Logging to logs\PPO_1 --------------------------------- | rollout/ | | | ep_len_mean | 174 | | ep_rew_mean | -0.0647 | | time/ | | | fps | 1087 | | iterations | 1 | | time_elapsed | 7 | | total_timesteps | 8192 | --------------------------------- ------------------------------------------- | rollout/ | | | ep_len_mean | 179 | | ep_rew_mean | -0.067 | | time/ | | | fps | 1034 | | iterations | 2 | | time_elapsed | 15 | | total_timesteps | 16384 | | train/ | | | approx_kl | 0.00053383934 | | clip_fraction | 0.00125 | | clip_range | 0.15 | | entropy_loss | -8.32 | | explained_variance | -9.76 | | learning_rate | 0.00025 | | loss | -0.00272 | | n_updates | 4 | | policy_gradient_loss | -0.000604 | | value_loss | 0.256 | ------------------------------------------- ------------------------------------------ | rollout/ | | | ep_len_mean | 192 | | ep_rew_mean | -0.0558 | | time/ | | | fps | 1040 | | iterations | 3 | | time_elapsed | 23 | | total_timesteps | 24576 | | train/ | | | approx_kl | 0.0037626293 | | clip_fraction | 0.0411 | | clip_range | 0.15 | | entropy_loss | -8.31 | | explained_variance | -0.627 | | learning_rate | 0.00025 | | loss | -0.0254 | | n_updates | 8 | | policy_gradient_loss | -0.00986 | | value_loss | 0.0012 | ------------------------------------------ ----------------------------------------- | rollout/ | | | ep_len_mean | 198 | | ep_rew_mean | -0.0369 | | time/ | | | fps | 1045 | | iterations | 4 | | time_elapsed | 31 | | total_timesteps | 32768 | | train/ | | | approx_kl | 0.007358143 | | clip_fraction | 0.121 | | clip_range | 0.15 | | entropy_loss | -8.31 | | explained_variance | -1.67 | | learning_rate | 0.00025 | | loss | -0.0446 | | n_updates | 12 | | policy_gradient_loss | -0.0212 | | value_loss | 0.00197 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 199 | | ep_rew_mean | -0.0253 | | time/ | | | fps | 1048 | | iterations | 5 | | time_elapsed | 39 | | total_timesteps | 40960 | | train/ | | | approx_kl | 0.009054327 | | clip_fraction | 0.185 | | clip_range | 0.15 | | entropy_loss | -8.3 | | explained_variance | -2.35 | | learning_rate | 0.00025 | | loss | -0.0551 | | n_updates | 16 | | policy_gradient_loss | -0.0281 | | value_loss | 0.0018 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 202 | | ep_rew_mean | -0.0247 | | time/ | | | fps | 1046 | | iterations | 6 | | time_elapsed | 46 | | total_timesteps | 49152 | | train/ | | | approx_kl | 0.010547362 | | clip_fraction | 0.22 | | clip_range | 0.15 | | entropy_loss | -8.29 | | explained_variance | -1.96 | | learning_rate | 0.00025 | | loss | -0.0628 | | n_updates | 20 | | policy_gradient_loss | -0.0308 | | value_loss | 0.00197 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 196 | | ep_rew_mean | -0.0456 | | time/ | | | fps | 1043 | | iterations | 7 | | time_elapsed | 54 | | total_timesteps | 57344 | | train/ | | | approx_kl | 0.010614461 | | clip_fraction | 0.223 | | clip_range | 0.15 | | entropy_loss | -8.28 | | explained_variance | -2.08 | | learning_rate | 0.00025 | | loss | -0.0685 | | n_updates | 24 | | policy_gradient_loss | -0.0333 | | value_loss | 0.00176 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 200 | | ep_rew_mean | -0.039 | | time/ | | | fps | 1045 | | iterations | 8 | | time_elapsed | 62 | | total_timesteps | 65536 | | train/ | | | approx_kl | 0.013299786 | | clip_fraction | 0.252 | | clip_range | 0.15 | | entropy_loss | -8.27 | | explained_variance | -1.53 | | learning_rate | 0.00025 | | loss | -0.0662 | | n_updates | 28 | | policy_gradient_loss | -0.0366 | | value_loss | 0.00158 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 190 | | ep_rew_mean | -0.0768 | | time/ | | | fps | 1052 | | iterations | 9 | | time_elapsed | 70 | | total_timesteps | 73728 | | train/ | | | approx_kl | 0.013322118 | | clip_fraction | 0.266 | | clip_range | 0.15 | | entropy_loss | -8.27 | | explained_variance | -1.51 | | learning_rate | 0.00025 | | loss | -0.0729 | | n_updates | 32 | | policy_gradient_loss | -0.0384 | | value_loss | 0.00153 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 192 | | ep_rew_mean | -0.0579 | | time/ | | | fps | 1054 | | iterations | 10 | | time_elapsed | 77 | | total_timesteps | 81920 | | train/ | | | approx_kl | 0.013874512 | | clip_fraction | 0.282 | | clip_range | 0.15 | | entropy_loss | -8.26 | | explained_variance | -1.19 | | learning_rate | 0.00025 | | loss | -0.0734 | | n_updates | 36 | | policy_gradient_loss | -0.0395 | | value_loss | 0.00164 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 191 | | ep_rew_mean | -0.0485 | | time/ | | | fps | 1054 | | iterations | 11 | | time_elapsed | 85 | | total_timesteps | 90112 | | train/ | | | approx_kl | 0.014529864 | | clip_fraction | 0.275 | | clip_range | 0.15 | | entropy_loss | -8.26 | | explained_variance | -1.31 | | learning_rate | 0.00025 | | loss | -0.0746 | | n_updates | 40 | | policy_gradient_loss | -0.0408 | | value_loss | 0.00152 | ----------------------------------------- --------------------------------------- | rollout/ | | | ep_len_mean | 188 | | ep_rew_mean | -0.0494 | | time/ | | | fps | 1057 | | iterations | 12 | | time_elapsed | 93 | | total_timesteps | 98304 | | train/ | | | approx_kl | 0.0178392 | | clip_fraction | 0.302 | | clip_range | 0.15 | | entropy_loss | -8.24 | | explained_variance | -1.18 | | learning_rate | 0.00025 | | loss | -0.0763 | | n_updates | 44 | | policy_gradient_loss | -0.0421 | | value_loss | 0.00155 | --------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 194 | | ep_rew_mean | -0.0331 | | time/ | | | fps | 1055 | | iterations | 13 | | time_elapsed | 100 | | total_timesteps | 106496 | | train/ | | | approx_kl | 0.017949063 | | clip_fraction | 0.314 | | clip_range | 0.15 | | entropy_loss | -8.23 | | explained_variance | -0.914 | | learning_rate | 0.00025 | | loss | -0.0767 | | n_updates | 48 | | policy_gradient_loss | -0.0445 | | value_loss | 0.00161 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 197 | | ep_rew_mean | -0.0246 | | time/ | | | fps | 1056 | | iterations | 14 | | time_elapsed | 108 | | total_timesteps | 114688 | | train/ | | | approx_kl | 0.01733292 | | clip_fraction | 0.329 | | clip_range | 0.15 | | entropy_loss | -8.23 | | explained_variance | -1.2 | | learning_rate | 0.00025 | | loss | -0.0848 | | n_updates | 52 | | policy_gradient_loss | -0.0434 | | value_loss | 0.00128 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 199 | | ep_rew_mean | -0.0305 | | time/ | | | fps | 1056 | | iterations | 15 | | time_elapsed | 116 | | total_timesteps | 122880 | | train/ | | | approx_kl | 0.018736638 | | clip_fraction | 0.328 | | clip_range | 0.15 | | entropy_loss | -8.22 | | explained_variance | -0.864 | | learning_rate | 0.00025 | | loss | -0.077 | | n_updates | 56 | | policy_gradient_loss | -0.0443 | | value_loss | 0.00131 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 197 | | ep_rew_mean | -0.0437 | | time/ | | | fps | 1056 | | iterations | 16 | | time_elapsed | 124 | | total_timesteps | 131072 | | train/ | | | approx_kl | 0.021857463 | | clip_fraction | 0.33 | | clip_range | 0.15 | | entropy_loss | -8.22 | | explained_variance | -0.844 | | learning_rate | 0.00025 | | loss | -0.0745 | | n_updates | 60 | | policy_gradient_loss | -0.0446 | | value_loss | 0.0013 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 199 | | ep_rew_mean | -0.0267 | | time/ | | | fps | 1058 | | iterations | 17 | | time_elapsed | 131 | | total_timesteps | 139264 | | train/ | | | approx_kl | 0.020751465 | | clip_fraction | 0.331 | | clip_range | 0.15 | | entropy_loss | -8.21 | | explained_variance | -0.936 | | learning_rate | 0.00025 | | loss | -0.0813 | | n_updates | 64 | | policy_gradient_loss | -0.0463 | | value_loss | 0.00119 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 187 | | ep_rew_mean | -0.056 | | time/ | | | fps | 1059 | | iterations | 18 | | time_elapsed | 139 | | total_timesteps | 147456 | | train/ | | | approx_kl | 0.020477628 | | clip_fraction | 0.349 | | clip_range | 0.15 | | entropy_loss | -8.2 | | explained_variance | -0.762 | | learning_rate | 0.00025 | | loss | -0.0823 | | n_updates | 68 | | policy_gradient_loss | -0.0439 | | value_loss | 0.00118 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 186 | | ep_rew_mean | -0.0556 | | time/ | | | fps | 1062 | | iterations | 19 | | time_elapsed | 146 | | total_timesteps | 155648 | | train/ | | | approx_kl | 0.022180352 | | clip_fraction | 0.363 | | clip_range | 0.15 | | entropy_loss | -8.19 | | explained_variance | -0.655 | | learning_rate | 0.00025 | | loss | -0.0794 | | n_updates | 72 | | policy_gradient_loss | -0.0428 | | value_loss | 0.00114 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 196 | | ep_rew_mean | -0.0354 | | time/ | | | fps | 1064 | | iterations | 20 | | time_elapsed | 153 | | total_timesteps | 163840 | | train/ | | | approx_kl | 0.021395119 | | clip_fraction | 0.348 | | clip_range | 0.15 | | entropy_loss | -8.2 | | explained_variance | -0.451 | | learning_rate | 0.00025 | | loss | -0.0805 | | n_updates | 76 | | policy_gradient_loss | -0.043 | | value_loss | 0.00116 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 192 | | ep_rew_mean | -0.0657 | | time/ | | | fps | 1067 | | iterations | 21 | | time_elapsed | 161 | | total_timesteps | 172032 | | train/ | | | approx_kl | 0.022942461 | | clip_fraction | 0.35 | | clip_range | 0.15 | | entropy_loss | -8.19 | | explained_variance | -0.458 | | learning_rate | 0.00025 | | loss | -0.0818 | | n_updates | 80 | | policy_gradient_loss | -0.0476 | | value_loss | 0.000972 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 190 | | ep_rew_mean | -0.0618 | | time/ | | | fps | 1069 | | iterations | 22 | | time_elapsed | 168 | | total_timesteps | 180224 | | train/ | | | approx_kl | 0.02387139 | | clip_fraction | 0.35 | | clip_range | 0.15 | | entropy_loss | -8.18 | | explained_variance | -0.317 | | learning_rate | 0.00025 | | loss | -0.0754 | | n_updates | 84 | | policy_gradient_loss | -0.0438 | | value_loss | 0.00105 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 189 | | ep_rew_mean | -0.0452 | | time/ | | | fps | 1071 | | iterations | 23 | | time_elapsed | 175 | | total_timesteps | 188416 | | train/ | | | approx_kl | 0.022812603 | | clip_fraction | 0.348 | | clip_range | 0.15 | | entropy_loss | -8.18 | | explained_variance | -0.459 | | learning_rate | 0.00025 | | loss | -0.0818 | | n_updates | 88 | | policy_gradient_loss | -0.0473 | | value_loss | 0.000877 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 196 | | ep_rew_mean | -0.0406 | | time/ | | | fps | 1072 | | iterations | 24 | | time_elapsed | 183 | | total_timesteps | 196608 | | train/ | | | approx_kl | 0.024460688 | | clip_fraction | 0.351 | | clip_range | 0.15 | | entropy_loss | -8.18 | | explained_variance | -0.304 | | learning_rate | 0.00025 | | loss | -0.0792 | | n_updates | 92 | | policy_gradient_loss | -0.0465 | | value_loss | 0.000971 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 206 | | ep_rew_mean | -0.0107 | | time/ | | | fps | 1073 | | iterations | 25 | | time_elapsed | 190 | | total_timesteps | 204800 | | train/ | | | approx_kl | 0.02544355 | | clip_fraction | 0.377 | | clip_range | 0.15 | | entropy_loss | -8.17 | | explained_variance | -0.459 | | learning_rate | 0.00025 | | loss | -0.0787 | | n_updates | 96 | | policy_gradient_loss | -0.0475 | | value_loss | 0.000872 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 205 | | ep_rew_mean | -0.00389 | | time/ | | | fps | 1073 | | iterations | 26 | | time_elapsed | 198 | | total_timesteps | 212992 | | train/ | | | approx_kl | 0.02552393 | | clip_fraction | 0.377 | | clip_range | 0.15 | | entropy_loss | -8.16 | | explained_variance | -0.39 | | learning_rate | 0.000249 | | loss | -0.0795 | | n_updates | 100 | | policy_gradient_loss | -0.0452 | | value_loss | 0.000865 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 199 | | ep_rew_mean | -0.0245 | | time/ | | | fps | 1074 | | iterations | 27 | | time_elapsed | 205 | | total_timesteps | 221184 | | train/ | | | approx_kl | 0.025224393 | | clip_fraction | 0.37 | | clip_range | 0.15 | | entropy_loss | -8.16 | | explained_variance | -0.448 | | learning_rate | 0.000249 | | loss | -0.0854 | | n_updates | 104 | | policy_gradient_loss | -0.0464 | | value_loss | 0.000939 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 201 | | ep_rew_mean | -0.0211 | | time/ | | | fps | 1076 | | iterations | 28 | | time_elapsed | 212 | | total_timesteps | 229376 | | train/ | | | approx_kl | 0.026964266 | | clip_fraction | 0.392 | | clip_range | 0.15 | | entropy_loss | -8.15 | | explained_variance | -0.315 | | learning_rate | 0.000249 | | loss | -0.081 | | n_updates | 108 | | policy_gradient_loss | -0.0466 | | value_loss | 0.000904 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 209 | | ep_rew_mean | -0.0132 | | time/ | | | fps | 1077 | | iterations | 29 | | time_elapsed | 220 | | total_timesteps | 237568 | | train/ | | | approx_kl | 0.026146878 | | clip_fraction | 0.376 | | clip_range | 0.15 | | entropy_loss | -8.15 | | explained_variance | -0.265 | | learning_rate | 0.000249 | | loss | -0.0774 | | n_updates | 112 | | policy_gradient_loss | -0.0475 | | value_loss | 0.000817 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 200 | | ep_rew_mean | -0.0276 | | time/ | | | fps | 1077 | | iterations | 30 | | time_elapsed | 228 | | total_timesteps | 245760 | | train/ | | | approx_kl | 0.026943514 | | clip_fraction | 0.369 | | clip_range | 0.15 | | entropy_loss | -8.15 | | explained_variance | -0.225 | | learning_rate | 0.000249 | | loss | -0.0765 | | n_updates | 116 | | policy_gradient_loss | -0.0466 | | value_loss | 0.000774 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 195 | | ep_rew_mean | -0.0262 | | time/ | | | fps | 1077 | | iterations | 31 | | time_elapsed | 235 | | total_timesteps | 253952 | | train/ | | | approx_kl | 0.025579238 | | clip_fraction | 0.368 | | clip_range | 0.15 | | entropy_loss | -8.13 | | explained_variance | -0.139 | | learning_rate | 0.000249 | | loss | -0.0823 | | n_updates | 120 | | policy_gradient_loss | -0.0465 | | value_loss | 0.000845 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 201 | | ep_rew_mean | 0.00702 | | time/ | | | fps | 1078 | | iterations | 32 | | time_elapsed | 243 | | total_timesteps | 262144 | | train/ | | | approx_kl | 0.028000984 | | clip_fraction | 0.389 | | clip_range | 0.15 | | entropy_loss | -8.12 | | explained_variance | -0.202 | | learning_rate | 0.000249 | | loss | -0.0782 | | n_updates | 124 | | policy_gradient_loss | -0.0471 | | value_loss | 0.000711 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 211 | | ep_rew_mean | 0.0106 | | time/ | | | fps | 1079 | | iterations | 33 | | time_elapsed | 250 | | total_timesteps | 270336 | | train/ | | | approx_kl | 0.030560931 | | clip_fraction | 0.395 | | clip_range | 0.15 | | entropy_loss | -8.1 | | explained_variance | -0.211 | | learning_rate | 0.000249 | | loss | -0.0817 | | n_updates | 128 | | policy_gradient_loss | -0.046 | | value_loss | 0.000771 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 211 | | ep_rew_mean | 0.0104 | | time/ | | | fps | 1079 | | iterations | 34 | | time_elapsed | 257 | | total_timesteps | 278528 | | train/ | | | approx_kl | 0.029904656 | | clip_fraction | 0.381 | | clip_range | 0.15 | | entropy_loss | -8.09 | | explained_variance | -0.197 | | learning_rate | 0.000249 | | loss | -0.0792 | | n_updates | 132 | | policy_gradient_loss | -0.0467 | | value_loss | 0.00069 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 209 | | ep_rew_mean | 0.0087 | | time/ | | | fps | 1080 | | iterations | 35 | | time_elapsed | 265 | | total_timesteps | 286720 | | train/ | | | approx_kl | 0.03322889 | | clip_fraction | 0.419 | | clip_range | 0.15 | | entropy_loss | -8.07 | | explained_variance | -0.0905 | | learning_rate | 0.000249 | | loss | -0.0728 | | n_updates | 136 | | policy_gradient_loss | -0.0442 | | value_loss | 0.000856 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 204 | | ep_rew_mean | -0.00154 | | time/ | | | fps | 1081 | | iterations | 36 | | time_elapsed | 272 | | total_timesteps | 294912 | | train/ | | | approx_kl | 0.033368126 | | clip_fraction | 0.397 | | clip_range | 0.15 | | entropy_loss | -8.05 | | explained_variance | -0.111 | | learning_rate | 0.000249 | | loss | -0.0801 | | n_updates | 140 | | policy_gradient_loss | -0.047 | | value_loss | 0.000738 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 207 | | ep_rew_mean | 0.0033 | | time/ | | | fps | 1081 | | iterations | 37 | | time_elapsed | 280 | | total_timesteps | 303104 | | train/ | | | approx_kl | 0.03245949 | | clip_fraction | 0.407 | | clip_range | 0.15 | | entropy_loss | -8.07 | | explained_variance | -0.0745 | | learning_rate | 0.000249 | | loss | -0.0789 | | n_updates | 144 | | policy_gradient_loss | -0.0457 | | value_loss | 0.000775 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 211 | | ep_rew_mean | 0.0255 | | time/ | | | fps | 1081 | | iterations | 38 | | time_elapsed | 287 | | total_timesteps | 311296 | | train/ | | | approx_kl | 0.032103226 | | clip_fraction | 0.415 | | clip_range | 0.15 | | entropy_loss | -8.04 | | explained_variance | -0.0989 | | learning_rate | 0.000249 | | loss | -0.0837 | | n_updates | 148 | | policy_gradient_loss | -0.0457 | | value_loss | 0.000697 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 219 | | ep_rew_mean | 0.0341 | | time/ | | | fps | 1082 | | iterations | 39 | | time_elapsed | 295 | | total_timesteps | 319488 | | train/ | | | approx_kl | 0.03655534 | | clip_fraction | 0.425 | | clip_range | 0.15 | | entropy_loss | -8.03 | | explained_variance | -0.0782 | | learning_rate | 0.000249 | | loss | -0.078 | | n_updates | 152 | | policy_gradient_loss | -0.0459 | | value_loss | 0.000671 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 216 | | ep_rew_mean | 0.0226 | | time/ | | | fps | 1083 | | iterations | 40 | | time_elapsed | 302 | | total_timesteps | 327680 | | train/ | | | approx_kl | 0.032864608 | | clip_fraction | 0.416 | | clip_range | 0.15 | | entropy_loss | -8.03 | | explained_variance | -0.0368 | | learning_rate | 0.000249 | | loss | -0.0806 | | n_updates | 156 | | policy_gradient_loss | -0.0443 | | value_loss | 0.000702 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 208 | | ep_rew_mean | 0.0215 | | time/ | | | fps | 1083 | | iterations | 41 | | time_elapsed | 309 | | total_timesteps | 335872 | | train/ | | | approx_kl | 0.03296768 | | clip_fraction | 0.405 | | clip_range | 0.15 | | entropy_loss | -8.02 | | explained_variance | -0.0714 | | learning_rate | 0.000249 | | loss | -0.0841 | | n_updates | 160 | | policy_gradient_loss | -0.0456 | | value_loss | 0.000735 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 216 | | ep_rew_mean | 0.0384 | | time/ | | | fps | 1085 | | iterations | 42 | | time_elapsed | 317 | | total_timesteps | 344064 | | train/ | | | approx_kl | 0.034226447 | | clip_fraction | 0.41 | | clip_range | 0.15 | | entropy_loss | -8.02 | | explained_variance | -0.0433 | | learning_rate | 0.000249 | | loss | -0.0821 | | n_updates | 164 | | policy_gradient_loss | -0.0482 | | value_loss | 0.000689 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 215 | | ep_rew_mean | 0.0395 | | time/ | | | fps | 1085 | | iterations | 43 | | time_elapsed | 324 | | total_timesteps | 352256 | | train/ | | | approx_kl | 0.034567412 | | clip_fraction | 0.41 | | clip_range | 0.15 | | entropy_loss | -8.02 | | explained_variance | -0.0585 | | learning_rate | 0.000249 | | loss | -0.0759 | | n_updates | 168 | | policy_gradient_loss | -0.0473 | | value_loss | 0.000626 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 209 | | ep_rew_mean | 0.015 | | time/ | | | fps | 1085 | | iterations | 44 | | time_elapsed | 332 | | total_timesteps | 360448 | | train/ | | | approx_kl | 0.03582894 | | clip_fraction | 0.423 | | clip_range | 0.15 | | entropy_loss | -8 | | explained_variance | -0.069 | | learning_rate | 0.000249 | | loss | -0.0751 | | n_updates | 172 | | policy_gradient_loss | -0.0474 | | value_loss | 0.000647 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 197 | | ep_rew_mean | 0.0179 | | time/ | | | fps | 1086 | | iterations | 45 | | time_elapsed | 339 | | total_timesteps | 368640 | | train/ | | | approx_kl | 0.037727863 | | clip_fraction | 0.436 | | clip_range | 0.15 | | entropy_loss | -7.97 | | explained_variance | -0.0323 | | learning_rate | 0.000249 | | loss | -0.0803 | | n_updates | 176 | | policy_gradient_loss | -0.0468 | | value_loss | 0.000699 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 198 | | ep_rew_mean | 0.00253 | | time/ | | | fps | 1086 | | iterations | 46 | | time_elapsed | 346 | | total_timesteps | 376832 | | train/ | | | approx_kl | 0.036440752 | | clip_fraction | 0.426 | | clip_range | 0.15 | | entropy_loss | -7.96 | | explained_variance | -0.0603 | | learning_rate | 0.000249 | | loss | -0.0829 | | n_updates | 180 | | policy_gradient_loss | -0.0487 | | value_loss | 0.000727 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 205 | | ep_rew_mean | 0.0133 | | time/ | | | fps | 1087 | | iterations | 47 | | time_elapsed | 354 | | total_timesteps | 385024 | | train/ | | | approx_kl | 0.036603756 | | clip_fraction | 0.425 | | clip_range | 0.15 | | entropy_loss | -7.92 | | explained_variance | -0.0141 | | learning_rate | 0.000249 | | loss | -0.0719 | | n_updates | 184 | | policy_gradient_loss | -0.0439 | | value_loss | 0.000617 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 214 | | ep_rew_mean | 0.0356 | | time/ | | | fps | 1087 | | iterations | 48 | | time_elapsed | 361 | | total_timesteps | 393216 | | train/ | | | approx_kl | 0.038700864 | | clip_fraction | 0.436 | | clip_range | 0.15 | | entropy_loss | -7.93 | | explained_variance | -0.0768 | | learning_rate | 0.000249 | | loss | -0.0783 | | n_updates | 188 | | policy_gradient_loss | -0.0451 | | value_loss | 0.000707 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 212 | | ep_rew_mean | 0.0433 | | time/ | | | fps | 1087 | | iterations | 49 | | time_elapsed | 369 | | total_timesteps | 401408 | | train/ | | | approx_kl | 0.036966786 | | clip_fraction | 0.428 | | clip_range | 0.15 | | entropy_loss | -7.91 | | explained_variance | -0.0343 | | learning_rate | 0.000249 | | loss | -0.0739 | | n_updates | 192 | | policy_gradient_loss | -0.043 | | value_loss | 0.000676 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 216 | | ep_rew_mean | 0.0627 | | time/ | | | fps | 1087 | | iterations | 50 | | time_elapsed | 376 | | total_timesteps | 409600 | | train/ | | | approx_kl | 0.035639323 | | clip_fraction | 0.418 | | clip_range | 0.149 | | entropy_loss | -7.92 | | explained_variance | -0.0486 | | learning_rate | 0.000249 | | loss | -0.0771 | | n_updates | 196 | | policy_gradient_loss | -0.0471 | | value_loss | 0.00064 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 212 | | ep_rew_mean | 0.0701 | | time/ | | | fps | 1088 | | iterations | 51 | | time_elapsed | 383 | | total_timesteps | 417792 | | train/ | | | approx_kl | 0.03806825 | | clip_fraction | 0.42 | | clip_range | 0.149 | | entropy_loss | -7.92 | | explained_variance | -0.0104 | | learning_rate | 0.000249 | | loss | -0.0841 | | n_updates | 200 | | policy_gradient_loss | -0.0475 | | value_loss | 0.000615 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 211 | | ep_rew_mean | 0.0769 | | time/ | | | fps | 1088 | | iterations | 52 | | time_elapsed | 391 | | total_timesteps | 425984 | | train/ | | | approx_kl | 0.036555544 | | clip_fraction | 0.416 | | clip_range | 0.149 | | entropy_loss | -7.92 | | explained_variance | 0.0201 | | learning_rate | 0.000249 | | loss | -0.0819 | | n_updates | 204 | | policy_gradient_loss | -0.0469 | | value_loss | 0.000719 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 214 | | ep_rew_mean | 0.0708 | | time/ | | | fps | 1087 | | iterations | 53 | | time_elapsed | 399 | | total_timesteps | 434176 | | train/ | | | approx_kl | 0.038168434 | | clip_fraction | 0.427 | | clip_range | 0.149 | | entropy_loss | -7.87 | | explained_variance | -0.0123 | | learning_rate | 0.000249 | | loss | -0.0781 | | n_updates | 208 | | policy_gradient_loss | -0.0468 | | value_loss | 0.000713 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 215 | | ep_rew_mean | 0.0726 | | time/ | | | fps | 1087 | | iterations | 54 | | time_elapsed | 406 | | total_timesteps | 442368 | | train/ | | | approx_kl | 0.04196939 | | clip_fraction | 0.427 | | clip_range | 0.149 | | entropy_loss | -7.9 | | explained_variance | -0.0342 | | learning_rate | 0.000249 | | loss | -0.0772 | | n_updates | 212 | | policy_gradient_loss | -0.0478 | | value_loss | 0.000688 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 208 | | ep_rew_mean | 0.0344 | | time/ | | | fps | 1088 | | iterations | 55 | | time_elapsed | 414 | | total_timesteps | 450560 | | train/ | | | approx_kl | 0.036647327 | | clip_fraction | 0.426 | | clip_range | 0.149 | | entropy_loss | -7.92 | | explained_variance | -0.0315 | | learning_rate | 0.000249 | | loss | -0.0857 | | n_updates | 216 | | policy_gradient_loss | -0.0484 | | value_loss | 0.000633 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 203 | | ep_rew_mean | 0.0314 | | time/ | | | fps | 1088 | | iterations | 56 | | time_elapsed | 421 | | total_timesteps | 458752 | | train/ | | | approx_kl | 0.04033483 | | clip_fraction | 0.431 | | clip_range | 0.149 | | entropy_loss | -7.87 | | explained_variance | -0.0516 | | learning_rate | 0.000249 | | loss | -0.0824 | | n_updates | 220 | | policy_gradient_loss | -0.047 | | value_loss | 0.000681 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 203 | | ep_rew_mean | 0.00718 | | time/ | | | fps | 1088 | | iterations | 57 | | time_elapsed | 429 | | total_timesteps | 466944 | | train/ | | | approx_kl | 0.041999236 | | clip_fraction | 0.449 | | clip_range | 0.149 | | entropy_loss | -7.82 | | explained_variance | -0.0333 | | learning_rate | 0.000249 | | loss | -0.0882 | | n_updates | 224 | | policy_gradient_loss | -0.0478 | | value_loss | 0.000702 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 209 | | ep_rew_mean | 0.0356 | | time/ | | | fps | 1088 | | iterations | 58 | | time_elapsed | 436 | | total_timesteps | 475136 | | train/ | | | approx_kl | 0.043302666 | | clip_fraction | 0.443 | | clip_range | 0.149 | | entropy_loss | -7.78 | | explained_variance | -0.0384 | | learning_rate | 0.000249 | | loss | -0.0746 | | n_updates | 228 | | policy_gradient_loss | -0.0451 | | value_loss | 0.00069 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 208 | | ep_rew_mean | 0.0532 | | time/ | | | fps | 1089 | | iterations | 59 | | time_elapsed | 443 | | total_timesteps | 483328 | | train/ | | | approx_kl | 0.05051574 | | clip_fraction | 0.468 | | clip_range | 0.149 | | entropy_loss | -7.72 | | explained_variance | 0.0441 | | learning_rate | 0.000249 | | loss | -0.0727 | | n_updates | 232 | | policy_gradient_loss | -0.0466 | | value_loss | 0.000701 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 211 | | ep_rew_mean | 0.0803 | | time/ | | | fps | 1090 | | iterations | 60 | | time_elapsed | 450 | | total_timesteps | 491520 | | train/ | | | approx_kl | 0.046735413 | | clip_fraction | 0.475 | | clip_range | 0.149 | | entropy_loss | -7.69 | | explained_variance | -0.0132 | | learning_rate | 0.000249 | | loss | -0.0811 | | n_updates | 236 | | policy_gradient_loss | -0.0477 | | value_loss | 0.000733 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 215 | | ep_rew_mean | 0.0944 | | time/ | | | fps | 1090 | | iterations | 61 | | time_elapsed | 458 | | total_timesteps | 499712 | | train/ | | | approx_kl | 0.048767954 | | clip_fraction | 0.469 | | clip_range | 0.149 | | entropy_loss | -7.66 | | explained_variance | 0.0494 | | learning_rate | 0.000249 | | loss | -0.0812 | | n_updates | 240 | | policy_gradient_loss | -0.046 | | value_loss | 0.000634 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 219 | | ep_rew_mean | 0.0853 | | time/ | | | fps | 1090 | | iterations | 62 | | time_elapsed | 465 | | total_timesteps | 507904 | | train/ | | | approx_kl | 0.048191354 | | clip_fraction | 0.473 | | clip_range | 0.149 | | entropy_loss | -7.65 | | explained_variance | -0.0291 | | learning_rate | 0.000249 | | loss | -0.0774 | | n_updates | 244 | | policy_gradient_loss | -0.0459 | | value_loss | 0.000682 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 224 | | ep_rew_mean | 0.0819 | | time/ | | | fps | 1090 | | iterations | 63 | | time_elapsed | 473 | | total_timesteps | 516096 | | train/ | | | approx_kl | 0.04908924 | | clip_fraction | 0.474 | | clip_range | 0.149 | | entropy_loss | -7.7 | | explained_variance | -0.0348 | | learning_rate | 0.000249 | | loss | -0.0752 | | n_updates | 248 | | policy_gradient_loss | -0.0459 | | value_loss | 0.000703 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 224 | | ep_rew_mean | 0.0891 | | time/ | | | fps | 1090 | | iterations | 64 | | time_elapsed | 480 | | total_timesteps | 524288 | | train/ | | | approx_kl | 0.046627633 | | clip_fraction | 0.467 | | clip_range | 0.149 | | entropy_loss | -7.65 | | explained_variance | 0.00435 | | learning_rate | 0.000249 | | loss | -0.085 | | n_updates | 252 | | policy_gradient_loss | -0.047 | | value_loss | 0.000702 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 215 | | ep_rew_mean | 0.0887 | | time/ | | | fps | 1091 | | iterations | 65 | | time_elapsed | 487 | | total_timesteps | 532480 | | train/ | | | approx_kl | 0.04555271 | | clip_fraction | 0.472 | | clip_range | 0.149 | | entropy_loss | -7.65 | | explained_variance | 0.0458 | | learning_rate | 0.000249 | | loss | -0.0808 | | n_updates | 256 | | policy_gradient_loss | -0.0452 | | value_loss | 0.000659 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 214 | | ep_rew_mean | 0.0925 | | time/ | | | fps | 1092 | | iterations | 66 | | time_elapsed | 495 | | total_timesteps | 540672 | | train/ | | | approx_kl | 0.046878427 | | clip_fraction | 0.459 | | clip_range | 0.149 | | entropy_loss | -7.64 | | explained_variance | 0.074 | | learning_rate | 0.000249 | | loss | -0.0829 | | n_updates | 260 | | policy_gradient_loss | -0.0477 | | value_loss | 0.000736 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 223 | | ep_rew_mean | 0.109 | | time/ | | | fps | 1092 | | iterations | 67 | | time_elapsed | 502 | | total_timesteps | 548864 | | train/ | | | approx_kl | 0.052148454 | | clip_fraction | 0.478 | | clip_range | 0.149 | | entropy_loss | -7.63 | | explained_variance | 0.00465 | | learning_rate | 0.000249 | | loss | -0.0765 | | n_updates | 264 | | policy_gradient_loss | -0.0493 | | value_loss | 0.000697 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 239 | | ep_rew_mean | 0.136 | | time/ | | | fps | 1092 | | iterations | 68 | | time_elapsed | 509 | | total_timesteps | 557056 | | train/ | | | approx_kl | 0.05289767 | | clip_fraction | 0.473 | | clip_range | 0.149 | | entropy_loss | -7.65 | | explained_variance | 0.0173 | | learning_rate | 0.000249 | | loss | -0.0791 | | n_updates | 268 | | policy_gradient_loss | -0.0484 | | value_loss | 0.000694 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 232 | | ep_rew_mean | 0.129 | | time/ | | | fps | 1092 | | iterations | 69 | | time_elapsed | 517 | | total_timesteps | 565248 | | train/ | | | approx_kl | 0.04817179 | | clip_fraction | 0.454 | | clip_range | 0.149 | | entropy_loss | -7.63 | | explained_variance | 0.0719 | | learning_rate | 0.000249 | | loss | -0.0816 | | n_updates | 272 | | policy_gradient_loss | -0.048 | | value_loss | 0.000655 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 226 | | ep_rew_mean | 0.0997 | | time/ | | | fps | 1093 | | iterations | 70 | | time_elapsed | 524 | | total_timesteps | 573440 | | train/ | | | approx_kl | 0.042836964 | | clip_fraction | 0.464 | | clip_range | 0.149 | | entropy_loss | -7.61 | | explained_variance | 0.0555 | | learning_rate | 0.000249 | | loss | -0.0779 | | n_updates | 276 | | policy_gradient_loss | -0.0442 | | value_loss | 0.000752 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 222 | | ep_rew_mean | 0.108 | | time/ | | | fps | 1092 | | iterations | 71 | | time_elapsed | 532 | | total_timesteps | 581632 | | train/ | | | approx_kl | 0.050688475 | | clip_fraction | 0.456 | | clip_range | 0.149 | | entropy_loss | -7.66 | | explained_variance | 0.0707 | | learning_rate | 0.000249 | | loss | -0.0782 | | n_updates | 280 | | policy_gradient_loss | -0.0494 | | value_loss | 0.000642 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 223 | | ep_rew_mean | 0.101 | | time/ | | | fps | 1093 | | iterations | 72 | | time_elapsed | 539 | | total_timesteps | 589824 | | train/ | | | approx_kl | 0.04820112 | | clip_fraction | 0.451 | | clip_range | 0.149 | | entropy_loss | -7.65 | | explained_variance | 0.129 | | learning_rate | 0.000249 | | loss | -0.0823 | | n_updates | 284 | | policy_gradient_loss | -0.0507 | | value_loss | 0.000645 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 225 | | ep_rew_mean | 0.125 | | time/ | | | fps | 1093 | | iterations | 73 | | time_elapsed | 547 | | total_timesteps | 598016 | | train/ | | | approx_kl | 0.04895016 | | clip_fraction | 0.458 | | clip_range | 0.149 | | entropy_loss | -7.67 | | explained_variance | 0.152 | | learning_rate | 0.000249 | | loss | -0.0872 | | n_updates | 288 | | policy_gradient_loss | -0.0491 | | value_loss | 0.000627 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 227 | | ep_rew_mean | 0.123 | | time/ | | | fps | 1093 | | iterations | 74 | | time_elapsed | 554 | | total_timesteps | 606208 | | train/ | | | approx_kl | 0.051398568 | | clip_fraction | 0.472 | | clip_range | 0.149 | | entropy_loss | -7.66 | | explained_variance | 0.128 | | learning_rate | 0.000249 | | loss | -0.087 | | n_updates | 292 | | policy_gradient_loss | -0.0499 | | value_loss | 0.000634 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 231 | | ep_rew_mean | 0.149 | | time/ | | | fps | 1093 | | iterations | 75 | | time_elapsed | 561 | | total_timesteps | 614400 | | train/ | | | approx_kl | 0.047108963 | | clip_fraction | 0.454 | | clip_range | 0.149 | | entropy_loss | -7.63 | | explained_variance | 0.145 | | learning_rate | 0.000248 | | loss | -0.0819 | | n_updates | 296 | | policy_gradient_loss | -0.0492 | | value_loss | 0.000631 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 227 | | ep_rew_mean | 0.165 | | time/ | | | fps | 1093 | | iterations | 76 | | time_elapsed | 569 | | total_timesteps | 622592 | | train/ | | | approx_kl | 0.047998037 | | clip_fraction | 0.465 | | clip_range | 0.149 | | entropy_loss | -7.61 | | explained_variance | 0.157 | | learning_rate | 0.000248 | | loss | -0.086 | | n_updates | 300 | | policy_gradient_loss | -0.0498 | | value_loss | 0.000741 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 230 | | ep_rew_mean | 0.162 | | time/ | | | fps | 1093 | | iterations | 77 | | time_elapsed | 576 | | total_timesteps | 630784 | | train/ | | | approx_kl | 0.052043833 | | clip_fraction | 0.461 | | clip_range | 0.149 | | entropy_loss | -7.64 | | explained_variance | 0.193 | | learning_rate | 0.000248 | | loss | -0.0856 | | n_updates | 304 | | policy_gradient_loss | -0.0505 | | value_loss | 0.00071 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 227 | | ep_rew_mean | 0.146 | | time/ | | | fps | 1094 | | iterations | 78 | | time_elapsed | 583 | | total_timesteps | 638976 | | train/ | | | approx_kl | 0.05115318 | | clip_fraction | 0.455 | | clip_range | 0.149 | | entropy_loss | -7.62 | | explained_variance | 0.144 | | learning_rate | 0.000248 | | loss | -0.0829 | | n_updates | 308 | | policy_gradient_loss | -0.05 | | value_loss | 0.000655 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 225 | | ep_rew_mean | 0.123 | | time/ | | | fps | 1094 | | iterations | 79 | | time_elapsed | 591 | | total_timesteps | 647168 | | train/ | | | approx_kl | 0.05336699 | | clip_fraction | 0.472 | | clip_range | 0.149 | | entropy_loss | -7.6 | | explained_variance | 0.162 | | learning_rate | 0.000248 | | loss | -0.0846 | | n_updates | 312 | | policy_gradient_loss | -0.0494 | | value_loss | 0.000681 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 224 | | ep_rew_mean | 0.125 | | time/ | | | fps | 1094 | | iterations | 80 | | time_elapsed | 599 | | total_timesteps | 655360 | | train/ | | | approx_kl | 0.050866805 | | clip_fraction | 0.467 | | clip_range | 0.149 | | entropy_loss | -7.57 | | explained_variance | 0.148 | | learning_rate | 0.000248 | | loss | -0.0788 | | n_updates | 316 | | policy_gradient_loss | -0.0474 | | value_loss | 0.000746 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 220 | | ep_rew_mean | 0.137 | | time/ | | | fps | 1093 | | iterations | 81 | | time_elapsed | 606 | | total_timesteps | 663552 | | train/ | | | approx_kl | 0.056692705 | | clip_fraction | 0.485 | | clip_range | 0.149 | | entropy_loss | -7.56 | | explained_variance | 0.154 | | learning_rate | 0.000248 | | loss | -0.081 | | n_updates | 320 | | policy_gradient_loss | -0.0493 | | value_loss | 0.000719 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 222 | | ep_rew_mean | 0.151 | | time/ | | | fps | 1094 | | iterations | 82 | | time_elapsed | 613 | | total_timesteps | 671744 | | train/ | | | approx_kl | 0.049499568 | | clip_fraction | 0.459 | | clip_range | 0.149 | | entropy_loss | -7.62 | | explained_variance | 0.104 | | learning_rate | 0.000248 | | loss | -0.0791 | | n_updates | 324 | | policy_gradient_loss | -0.051 | | value_loss | 0.000771 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 213 | | ep_rew_mean | 0.129 | | time/ | | | fps | 1094 | | iterations | 83 | | time_elapsed | 621 | | total_timesteps | 679936 | | train/ | | | approx_kl | 0.051906064 | | clip_fraction | 0.463 | | clip_range | 0.149 | | entropy_loss | -7.61 | | explained_variance | 0.136 | | learning_rate | 0.000248 | | loss | -0.0775 | | n_updates | 328 | | policy_gradient_loss | -0.0501 | | value_loss | 0.00071 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 216 | | ep_rew_mean | 0.134 | | time/ | | | fps | 1094 | | iterations | 84 | | time_elapsed | 628 | | total_timesteps | 688128 | | train/ | | | approx_kl | 0.049262717 | | clip_fraction | 0.474 | | clip_range | 0.149 | | entropy_loss | -7.61 | | explained_variance | 0.152 | | learning_rate | 0.000248 | | loss | -0.0761 | | n_updates | 332 | | policy_gradient_loss | -0.0481 | | value_loss | 0.000789 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 217 | | ep_rew_mean | 0.146 | | time/ | | | fps | 1094 | | iterations | 85 | | time_elapsed | 635 | | total_timesteps | 696320 | | train/ | | | approx_kl | 0.050139796 | | clip_fraction | 0.459 | | clip_range | 0.149 | | entropy_loss | -7.57 | | explained_variance | 0.19 | | learning_rate | 0.000248 | | loss | -0.0825 | | n_updates | 336 | | policy_gradient_loss | -0.0484 | | value_loss | 0.000759 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 221 | | ep_rew_mean | 0.13 | | time/ | | | fps | 1095 | | iterations | 86 | | time_elapsed | 643 | | total_timesteps | 704512 | | train/ | | | approx_kl | 0.05926934 | | clip_fraction | 0.48 | | clip_range | 0.149 | | entropy_loss | -7.57 | | explained_variance | 0.27 | | learning_rate | 0.000248 | | loss | -0.0783 | | n_updates | 340 | | policy_gradient_loss | -0.0502 | | value_loss | 0.00066 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 222 | | ep_rew_mean | 0.135 | | time/ | | | fps | 1095 | | iterations | 87 | | time_elapsed | 650 | | total_timesteps | 712704 | | train/ | | | approx_kl | 0.052811056 | | clip_fraction | 0.47 | | clip_range | 0.149 | | entropy_loss | -7.58 | | explained_variance | 0.14 | | learning_rate | 0.000248 | | loss | -0.0827 | | n_updates | 344 | | policy_gradient_loss | -0.051 | | value_loss | 0.000671 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 224 | | ep_rew_mean | 0.154 | | time/ | | | fps | 1094 | | iterations | 88 | | time_elapsed | 658 | | total_timesteps | 720896 | | train/ | | | approx_kl | 0.05576945 | | clip_fraction | 0.47 | | clip_range | 0.149 | | entropy_loss | -7.56 | | explained_variance | 0.193 | | learning_rate | 0.000248 | | loss | -0.0812 | | n_updates | 348 | | policy_gradient_loss | -0.0511 | | value_loss | 0.000725 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 236 | | ep_rew_mean | 0.185 | | time/ | | | fps | 1095 | | iterations | 89 | | time_elapsed | 665 | | total_timesteps | 729088 | | train/ | | | approx_kl | 0.05484263 | | clip_fraction | 0.477 | | clip_range | 0.149 | | entropy_loss | -7.58 | | explained_variance | 0.26 | | learning_rate | 0.000248 | | loss | -0.0755 | | n_updates | 352 | | policy_gradient_loss | -0.0505 | | value_loss | 0.000608 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 237 | | ep_rew_mean | 0.18 | | time/ | | | fps | 1095 | | iterations | 90 | | time_elapsed | 673 | | total_timesteps | 737280 | | train/ | | | approx_kl | 0.053323437 | | clip_fraction | 0.483 | | clip_range | 0.149 | | entropy_loss | -7.56 | | explained_variance | 0.298 | | learning_rate | 0.000248 | | loss | -0.0808 | | n_updates | 356 | | policy_gradient_loss | -0.049 | | value_loss | 0.000648 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 240 | | ep_rew_mean | 0.188 | | time/ | | | fps | 1095 | | iterations | 91 | | time_elapsed | 680 | | total_timesteps | 745472 | | train/ | | | approx_kl | 0.05433871 | | clip_fraction | 0.478 | | clip_range | 0.149 | | entropy_loss | -7.55 | | explained_variance | 0.394 | | learning_rate | 0.000248 | | loss | -0.0876 | | n_updates | 360 | | policy_gradient_loss | -0.048 | | value_loss | 0.0006 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 235 | | ep_rew_mean | 0.203 | | time/ | | | fps | 1096 | | iterations | 92 | | time_elapsed | 687 | | total_timesteps | 753664 | | train/ | | | approx_kl | 0.05357936 | | clip_fraction | 0.485 | | clip_range | 0.149 | | entropy_loss | -7.53 | | explained_variance | 0.346 | | learning_rate | 0.000248 | | loss | -0.0864 | | n_updates | 364 | | policy_gradient_loss | -0.0467 | | value_loss | 0.000691 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 228 | | ep_rew_mean | 0.191 | | time/ | | | fps | 1096 | | iterations | 93 | | time_elapsed | 694 | | total_timesteps | 761856 | | train/ | | | approx_kl | 0.058348823 | | clip_fraction | 0.483 | | clip_range | 0.149 | | entropy_loss | -7.56 | | explained_variance | 0.342 | | learning_rate | 0.000248 | | loss | -0.0833 | | n_updates | 368 | | policy_gradient_loss | -0.0499 | | value_loss | 0.000693 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 230 | | ep_rew_mean | 0.176 | | time/ | | | fps | 1096 | | iterations | 94 | | time_elapsed | 702 | | total_timesteps | 770048 | | train/ | | | approx_kl | 0.049724404 | | clip_fraction | 0.461 | | clip_range | 0.149 | | entropy_loss | -7.5 | | explained_variance | 0.35 | | learning_rate | 0.000248 | | loss | -0.0754 | | n_updates | 372 | | policy_gradient_loss | -0.0442 | | value_loss | 0.000803 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 227 | | ep_rew_mean | 0.157 | | time/ | | | fps | 1097 | | iterations | 95 | | time_elapsed | 709 | | total_timesteps | 778240 | | train/ | | | approx_kl | 0.053371284 | | clip_fraction | 0.473 | | clip_range | 0.149 | | entropy_loss | -7.52 | | explained_variance | 0.429 | | learning_rate | 0.000248 | | loss | -0.079 | | n_updates | 376 | | policy_gradient_loss | -0.0486 | | value_loss | 0.000602 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 237 | | ep_rew_mean | 0.181 | | time/ | | | fps | 1097 | | iterations | 96 | | time_elapsed | 716 | | total_timesteps | 786432 | | train/ | | | approx_kl | 0.055270787 | | clip_fraction | 0.475 | | clip_range | 0.149 | | entropy_loss | -7.45 | | explained_variance | 0.437 | | learning_rate | 0.000248 | | loss | -0.0825 | | n_updates | 380 | | policy_gradient_loss | -0.0482 | | value_loss | 0.00063 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 230 | | ep_rew_mean | 0.185 | | time/ | | | fps | 1097 | | iterations | 97 | | time_elapsed | 724 | | total_timesteps | 794624 | | train/ | | | approx_kl | 0.056365583 | | clip_fraction | 0.482 | | clip_range | 0.149 | | entropy_loss | -7.44 | | explained_variance | 0.399 | | learning_rate | 0.000248 | | loss | -0.0673 | | n_updates | 384 | | policy_gradient_loss | -0.0465 | | value_loss | 0.000653 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 230 | | ep_rew_mean | 0.213 | | time/ | | | fps | 1097 | | iterations | 98 | | time_elapsed | 731 | | total_timesteps | 802816 | | train/ | | | approx_kl | 0.05440127 | | clip_fraction | 0.467 | | clip_range | 0.149 | | entropy_loss | -7.46 | | explained_variance | 0.43 | | learning_rate | 0.000248 | | loss | -0.0791 | | n_updates | 388 | | policy_gradient_loss | -0.0496 | | value_loss | 0.00059 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 234 | | ep_rew_mean | 0.221 | | time/ | | | fps | 1097 | | iterations | 99 | | time_elapsed | 738 | | total_timesteps | 811008 | | train/ | | | approx_kl | 0.05217243 | | clip_fraction | 0.466 | | clip_range | 0.149 | | entropy_loss | -7.42 | | explained_variance | 0.41 | | learning_rate | 0.000248 | | loss | -0.0794 | | n_updates | 392 | | policy_gradient_loss | -0.0479 | | value_loss | 0.000771 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 243 | | ep_rew_mean | 0.237 | | time/ | | | fps | 1097 | | iterations | 100 | | time_elapsed | 746 | | total_timesteps | 819200 | | train/ | | | approx_kl | 0.05560397 | | clip_fraction | 0.468 | | clip_range | 0.149 | | entropy_loss | -7.48 | | explained_variance | 0.448 | | learning_rate | 0.000248 | | loss | -0.0777 | | n_updates | 396 | | policy_gradient_loss | -0.0482 | | value_loss | 0.000607 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 245 | | ep_rew_mean | 0.244 | | time/ | | | fps | 1098 | | iterations | 101 | | time_elapsed | 753 | | total_timesteps | 827392 | | train/ | | | approx_kl | 0.05901387 | | clip_fraction | 0.471 | | clip_range | 0.149 | | entropy_loss | -7.45 | | explained_variance | 0.457 | | learning_rate | 0.000248 | | loss | -0.0752 | | n_updates | 400 | | policy_gradient_loss | -0.0466 | | value_loss | 0.000684 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 241 | | ep_rew_mean | 0.238 | | time/ | | | fps | 1098 | | iterations | 102 | | time_elapsed | 760 | | total_timesteps | 835584 | | train/ | | | approx_kl | 0.052878335 | | clip_fraction | 0.477 | | clip_range | 0.149 | | entropy_loss | -7.45 | | explained_variance | 0.402 | | learning_rate | 0.000248 | | loss | -0.0702 | | n_updates | 404 | | policy_gradient_loss | -0.0466 | | value_loss | 0.000757 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 243 | | ep_rew_mean | 0.242 | | time/ | | | fps | 1098 | | iterations | 103 | | time_elapsed | 768 | | total_timesteps | 843776 | | train/ | | | approx_kl | 0.059576597 | | clip_fraction | 0.474 | | clip_range | 0.149 | | entropy_loss | -7.41 | | explained_variance | 0.428 | | learning_rate | 0.000248 | | loss | -0.0806 | | n_updates | 408 | | policy_gradient_loss | -0.0505 | | value_loss | 0.000688 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 240 | | ep_rew_mean | 0.222 | | time/ | | | fps | 1098 | | iterations | 104 | | time_elapsed | 775 | | total_timesteps | 851968 | | train/ | | | approx_kl | 0.056462698 | | clip_fraction | 0.471 | | clip_range | 0.149 | | entropy_loss | -7.47 | | explained_variance | 0.414 | | learning_rate | 0.000248 | | loss | -0.0808 | | n_updates | 412 | | policy_gradient_loss | -0.051 | | value_loss | 0.000587 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 230 | | ep_rew_mean | 0.198 | | time/ | | | fps | 1098 | | iterations | 105 | | time_elapsed | 782 | | total_timesteps | 860160 | | train/ | | | approx_kl | 0.053794455 | | clip_fraction | 0.471 | | clip_range | 0.149 | | entropy_loss | -7.42 | | explained_variance | 0.396 | | learning_rate | 0.000248 | | loss | -0.083 | | n_updates | 416 | | policy_gradient_loss | -0.0473 | | value_loss | 0.000671 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 228 | | ep_rew_mean | 0.206 | | time/ | | | fps | 1098 | | iterations | 106 | | time_elapsed | 790 | | total_timesteps | 868352 | | train/ | | | approx_kl | 0.05114977 | | clip_fraction | 0.463 | | clip_range | 0.149 | | entropy_loss | -7.47 | | explained_variance | 0.438 | | learning_rate | 0.000248 | | loss | -0.0808 | | n_updates | 420 | | policy_gradient_loss | -0.048 | | value_loss | 0.000614 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 226 | | ep_rew_mean | 0.199 | | time/ | | | fps | 1098 | | iterations | 107 | | time_elapsed | 797 | | total_timesteps | 876544 | | train/ | | | approx_kl | 0.04553146 | | clip_fraction | 0.443 | | clip_range | 0.149 | | entropy_loss | -7.5 | | explained_variance | 0.523 | | learning_rate | 0.000248 | | loss | -0.0804 | | n_updates | 424 | | policy_gradient_loss | -0.0462 | | value_loss | 0.000607 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 229 | | ep_rew_mean | 0.227 | | time/ | | | fps | 1098 | | iterations | 108 | | time_elapsed | 805 | | total_timesteps | 884736 | | train/ | | | approx_kl | 0.05251344 | | clip_fraction | 0.459 | | clip_range | 0.149 | | entropy_loss | -7.5 | | explained_variance | 0.484 | | learning_rate | 0.000248 | | loss | -0.0821 | | n_updates | 428 | | policy_gradient_loss | -0.0505 | | value_loss | 0.000639 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 226 | | ep_rew_mean | 0.216 | | time/ | | | fps | 1099 | | iterations | 109 | | time_elapsed | 812 | | total_timesteps | 892928 | | train/ | | | approx_kl | 0.05173687 | | clip_fraction | 0.445 | | clip_range | 0.149 | | entropy_loss | -7.48 | | explained_variance | 0.422 | | learning_rate | 0.000248 | | loss | -0.076 | | n_updates | 432 | | policy_gradient_loss | -0.0508 | | value_loss | 0.00073 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 235 | | ep_rew_mean | 0.229 | | time/ | | | fps | 1099 | | iterations | 110 | | time_elapsed | 819 | | total_timesteps | 901120 | | train/ | | | approx_kl | 0.052297696 | | clip_fraction | 0.461 | | clip_range | 0.149 | | entropy_loss | -7.53 | | explained_variance | 0.488 | | learning_rate | 0.000248 | | loss | -0.0845 | | n_updates | 436 | | policy_gradient_loss | -0.0504 | | value_loss | 0.000603 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 235 | | ep_rew_mean | 0.196 | | time/ | | | fps | 1099 | | iterations | 111 | | time_elapsed | 827 | | total_timesteps | 909312 | | train/ | | | approx_kl | 0.05267185 | | clip_fraction | 0.45 | | clip_range | 0.149 | | entropy_loss | -7.55 | | explained_variance | 0.397 | | learning_rate | 0.000248 | | loss | -0.0792 | | n_updates | 440 | | policy_gradient_loss | -0.0482 | | value_loss | 0.000686 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 240 | | ep_rew_mean | 0.196 | | time/ | | | fps | 1099 | | iterations | 112 | | time_elapsed | 834 | | total_timesteps | 917504 | | train/ | | | approx_kl | 0.050781623 | | clip_fraction | 0.451 | | clip_range | 0.149 | | entropy_loss | -7.53 | | explained_variance | 0.419 | | learning_rate | 0.000248 | | loss | -0.0802 | | n_updates | 444 | | policy_gradient_loss | -0.0498 | | value_loss | 0.000612 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 234 | | ep_rew_mean | 0.191 | | time/ | | | fps | 1099 | | iterations | 113 | | time_elapsed | 841 | | total_timesteps | 925696 | | train/ | | | approx_kl | 0.056232594 | | clip_fraction | 0.461 | | clip_range | 0.149 | | entropy_loss | -7.53 | | explained_variance | 0.432 | | learning_rate | 0.000248 | | loss | -0.0862 | | n_updates | 448 | | policy_gradient_loss | -0.0518 | | value_loss | 0.000616 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 231 | | ep_rew_mean | 0.201 | | time/ | | | fps | 1100 | | iterations | 114 | | time_elapsed | 848 | | total_timesteps | 933888 | | train/ | | | approx_kl | 0.05108821 | | clip_fraction | 0.449 | | clip_range | 0.149 | | entropy_loss | -7.52 | | explained_variance | 0.548 | | learning_rate | 0.000248 | | loss | -0.077 | | n_updates | 452 | | policy_gradient_loss | -0.0515 | | value_loss | 0.000543 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 230 | | ep_rew_mean | 0.204 | | time/ | | | fps | 1100 | | iterations | 115 | | time_elapsed | 856 | | total_timesteps | 942080 | | train/ | | | approx_kl | 0.05478944 | | clip_fraction | 0.459 | | clip_range | 0.149 | | entropy_loss | -7.48 | | explained_variance | 0.498 | | learning_rate | 0.000248 | | loss | -0.0769 | | n_updates | 456 | | policy_gradient_loss | -0.0476 | | value_loss | 0.000683 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 234 | | ep_rew_mean | 0.214 | | time/ | | | fps | 1100 | | iterations | 116 | | time_elapsed | 863 | | total_timesteps | 950272 | | train/ | | | approx_kl | 0.057544693 | | clip_fraction | 0.455 | | clip_range | 0.149 | | entropy_loss | -7.55 | | explained_variance | 0.481 | | learning_rate | 0.000248 | | loss | -0.0825 | | n_updates | 460 | | policy_gradient_loss | -0.052 | | value_loss | 0.000593 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 243 | | ep_rew_mean | 0.212 | | time/ | | | fps | 1100 | | iterations | 117 | | time_elapsed | 871 | | total_timesteps | 958464 | | train/ | | | approx_kl | 0.053028636 | | clip_fraction | 0.456 | | clip_range | 0.149 | | entropy_loss | -7.54 | | explained_variance | 0.419 | | learning_rate | 0.000248 | | loss | -0.0821 | | n_updates | 464 | | policy_gradient_loss | -0.0514 | | value_loss | 0.000663 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 250 | | ep_rew_mean | 0.232 | | time/ | | | fps | 1100 | | iterations | 118 | | time_elapsed | 878 | | total_timesteps | 966656 | | train/ | | | approx_kl | 0.05402498 | | clip_fraction | 0.449 | | clip_range | 0.149 | | entropy_loss | -7.51 | | explained_variance | 0.52 | | learning_rate | 0.000248 | | loss | -0.0773 | | n_updates | 468 | | policy_gradient_loss | -0.0504 | | value_loss | 0.000514 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 243 | | ep_rew_mean | 0.213 | | time/ | | | fps | 1100 | | iterations | 119 | | time_elapsed | 885 | | total_timesteps | 974848 | | train/ | | | approx_kl | 0.056870513 | | clip_fraction | 0.459 | | clip_range | 0.149 | | entropy_loss | -7.53 | | explained_variance | 0.457 | | learning_rate | 0.000248 | | loss | -0.0811 | | n_updates | 472 | | policy_gradient_loss | -0.0497 | | value_loss | 0.00064 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 243 | | ep_rew_mean | 0.223 | | time/ | | | fps | 1100 | | iterations | 120 | | time_elapsed | 893 | | total_timesteps | 983040 | | train/ | | | approx_kl | 0.062582076 | | clip_fraction | 0.468 | | clip_range | 0.149 | | entropy_loss | -7.51 | | explained_variance | 0.501 | | learning_rate | 0.000248 | | loss | -0.0759 | | n_updates | 476 | | policy_gradient_loss | -0.0513 | | value_loss | 0.000589 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 238 | | ep_rew_mean | 0.214 | | time/ | | | fps | 1100 | | iterations | 121 | | time_elapsed | 900 | | total_timesteps | 991232 | | train/ | | | approx_kl | 0.056241278 | | clip_fraction | 0.456 | | clip_range | 0.149 | | entropy_loss | -7.5 | | explained_variance | 0.482 | | learning_rate | 0.000248 | | loss | -0.0767 | | n_updates | 480 | | policy_gradient_loss | -0.0468 | | value_loss | 0.000643 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 237 | | ep_rew_mean | 0.233 | | time/ | | | fps | 1100 | | iterations | 122 | | time_elapsed | 908 | | total_timesteps | 999424 | | train/ | | | approx_kl | 0.059981856 | | clip_fraction | 0.461 | | clip_range | 0.149 | | entropy_loss | -7.47 | | explained_variance | 0.487 | | learning_rate | 0.000248 | | loss | -0.0846 | | n_updates | 484 | | policy_gradient_loss | -0.0503 | | value_loss | 0.000621 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 240 | | ep_rew_mean | 0.247 | | time/ | | | fps | 1100 | | iterations | 123 | | time_elapsed | 915 | | total_timesteps | 1007616 | | train/ | | | approx_kl | 0.06341614 | | clip_fraction | 0.466 | | clip_range | 0.149 | | entropy_loss | -7.44 | | explained_variance | 0.407 | | learning_rate | 0.000248 | | loss | -0.0819 | | n_updates | 488 | | policy_gradient_loss | -0.0497 | | value_loss | 0.000712 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 241 | | ep_rew_mean | 0.224 | | time/ | | | fps | 1100 | | iterations | 124 | | time_elapsed | 923 | | total_timesteps | 1015808 | | train/ | | | approx_kl | 0.062366627 | | clip_fraction | 0.468 | | clip_range | 0.149 | | entropy_loss | -7.47 | | explained_variance | 0.462 | | learning_rate | 0.000248 | | loss | -0.0792 | | n_updates | 492 | | policy_gradient_loss | -0.051 | | value_loss | 0.000579 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 236 | | ep_rew_mean | 0.217 | | time/ | | | fps | 1100 | | iterations | 125 | | time_elapsed | 930 | | total_timesteps | 1024000 | | train/ | | | approx_kl | 0.06348276 | | clip_fraction | 0.482 | | clip_range | 0.149 | | entropy_loss | -7.42 | | explained_variance | 0.5 | | learning_rate | 0.000247 | | loss | -0.0827 | | n_updates | 496 | | policy_gradient_loss | -0.0479 | | value_loss | 0.000599 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 239 | | ep_rew_mean | 0.234 | | time/ | | | fps | 1100 | | iterations | 126 | | time_elapsed | 938 | | total_timesteps | 1032192 | | train/ | | | approx_kl | 0.06243682 | | clip_fraction | 0.475 | | clip_range | 0.149 | | entropy_loss | -7.4 | | explained_variance | 0.504 | | learning_rate | 0.000247 | | loss | -0.079 | | n_updates | 500 | | policy_gradient_loss | -0.0477 | | value_loss | 0.000676 | ---------------------------------------- --------------------------------------- | rollout/ | | | ep_len_mean | 235 | | ep_rew_mean | 0.253 | | time/ | | | fps | 1100 | | iterations | 127 | | time_elapsed | 945 | | total_timesteps | 1040384 | | train/ | | | approx_kl | 0.0657691 | | clip_fraction | 0.477 | | clip_range | 0.149 | | entropy_loss | -7.42 | | explained_variance | 0.439 | | learning_rate | 0.000247 | | loss | -0.0825 | | n_updates | 504 | | policy_gradient_loss | -0.0494 | | value_loss | 0.000716 | --------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 237 | | ep_rew_mean | 0.255 | | time/ | | | fps | 1100 | | iterations | 128 | | time_elapsed | 953 | | total_timesteps | 1048576 | | train/ | | | approx_kl | 0.06508583 | | clip_fraction | 0.483 | | clip_range | 0.149 | | entropy_loss | -7.41 | | explained_variance | 0.451 | | learning_rate | 0.000247 | | loss | -0.0874 | | n_updates | 508 | | policy_gradient_loss | -0.0518 | | value_loss | 0.000709 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 243 | | ep_rew_mean | 0.259 | | time/ | | | fps | 1100 | | iterations | 129 | | time_elapsed | 960 | | total_timesteps | 1056768 | | train/ | | | approx_kl | 0.06456785 | | clip_fraction | 0.485 | | clip_range | 0.149 | | entropy_loss | -7.42 | | explained_variance | 0.484 | | learning_rate | 0.000247 | | loss | -0.0837 | | n_updates | 512 | | policy_gradient_loss | -0.051 | | value_loss | 0.000635 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 251 | | ep_rew_mean | 0.254 | | time/ | | | fps | 1101 | | iterations | 130 | | time_elapsed | 967 | | total_timesteps | 1064960 | | train/ | | | approx_kl | 0.06530982 | | clip_fraction | 0.486 | | clip_range | 0.149 | | entropy_loss | -7.41 | | explained_variance | 0.423 | | learning_rate | 0.000247 | | loss | -0.0849 | | n_updates | 516 | | policy_gradient_loss | -0.0514 | | value_loss | 0.000651 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 252 | | ep_rew_mean | 0.257 | | time/ | | | fps | 1100 | | iterations | 131 | | time_elapsed | 974 | | total_timesteps | 1073152 | | train/ | | | approx_kl | 0.06795773 | | clip_fraction | 0.484 | | clip_range | 0.149 | | entropy_loss | -7.43 | | explained_variance | 0.451 | | learning_rate | 0.000247 | | loss | -0.0793 | | n_updates | 520 | | policy_gradient_loss | -0.0525 | | value_loss | 0.000579 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 239 | | ep_rew_mean | 0.231 | | time/ | | | fps | 1101 | | iterations | 132 | | time_elapsed | 982 | | total_timesteps | 1081344 | | train/ | | | approx_kl | 0.06525904 | | clip_fraction | 0.476 | | clip_range | 0.149 | | entropy_loss | -7.38 | | explained_variance | 0.49 | | learning_rate | 0.000247 | | loss | -0.0683 | | n_updates | 524 | | policy_gradient_loss | -0.0502 | | value_loss | 0.000646 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 225 | | ep_rew_mean | 0.22 | | time/ | | | fps | 1100 | | iterations | 133 | | time_elapsed | 989 | | total_timesteps | 1089536 | | train/ | | | approx_kl | 0.06675568 | | clip_fraction | 0.478 | | clip_range | 0.149 | | entropy_loss | -7.47 | | explained_variance | 0.427 | | learning_rate | 0.000247 | | loss | -0.0805 | | n_updates | 528 | | policy_gradient_loss | -0.0517 | | value_loss | 0.000694 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 225 | | ep_rew_mean | 0.203 | | time/ | | | fps | 1100 | | iterations | 134 | | time_elapsed | 997 | | total_timesteps | 1097728 | | train/ | | | approx_kl | 0.059254743 | | clip_fraction | 0.471 | | clip_range | 0.149 | | entropy_loss | -7.4 | | explained_variance | 0.437 | | learning_rate | 0.000247 | | loss | -0.0709 | | n_updates | 532 | | policy_gradient_loss | -0.0471 | | value_loss | 0.000702 | ----------------------------------------- --------------------------------------- | rollout/ | | | ep_len_mean | 237 | | ep_rew_mean | 0.213 | | time/ | | | fps | 1100 | | iterations | 135 | | time_elapsed | 1004 | | total_timesteps | 1105920 | | train/ | | | approx_kl | 0.0610163 | | clip_fraction | 0.465 | | clip_range | 0.149 | | entropy_loss | -7.47 | | explained_variance | 0.461 | | learning_rate | 0.000247 | | loss | -0.0764 | | n_updates | 536 | | policy_gradient_loss | -0.0493 | | value_loss | 0.000674 | --------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 239 | | ep_rew_mean | 0.22 | | time/ | | | fps | 1101 | | iterations | 136 | | time_elapsed | 1011 | | total_timesteps | 1114112 | | train/ | | | approx_kl | 0.062838554 | | clip_fraction | 0.472 | | clip_range | 0.149 | | entropy_loss | -7.5 | | explained_variance | 0.483 | | learning_rate | 0.000247 | | loss | -0.0832 | | n_updates | 540 | | policy_gradient_loss | -0.0534 | | value_loss | 0.000604 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 237 | | ep_rew_mean | 0.205 | | time/ | | | fps | 1101 | | iterations | 137 | | time_elapsed | 1019 | | total_timesteps | 1122304 | | train/ | | | approx_kl | 0.060988206 | | clip_fraction | 0.47 | | clip_range | 0.149 | | entropy_loss | -7.5 | | explained_variance | 0.56 | | learning_rate | 0.000247 | | loss | -0.0823 | | n_updates | 544 | | policy_gradient_loss | -0.0516 | | value_loss | 0.000554 | ----------------------------------------- --------------------------------------- | rollout/ | | | ep_len_mean | 238 | | ep_rew_mean | 0.204 | | time/ | | | fps | 1101 | | iterations | 138 | | time_elapsed | 1026 | | total_timesteps | 1130496 | | train/ | | | approx_kl | 0.0639313 | | clip_fraction | 0.474 | | clip_range | 0.149 | | entropy_loss | -7.48 | | explained_variance | 0.51 | | learning_rate | 0.000247 | | loss | -0.0832 | | n_updates | 548 | | policy_gradient_loss | -0.051 | | value_loss | 0.000564 | --------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 234 | | ep_rew_mean | 0.212 | | time/ | | | fps | 1101 | | iterations | 139 | | time_elapsed | 1034 | | total_timesteps | 1138688 | | train/ | | | approx_kl | 0.07040946 | | clip_fraction | 0.501 | | clip_range | 0.149 | | entropy_loss | -7.42 | | explained_variance | 0.483 | | learning_rate | 0.000247 | | loss | -0.0774 | | n_updates | 552 | | policy_gradient_loss | -0.0516 | | value_loss | 0.000648 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 238 | | ep_rew_mean | 0.257 | | time/ | | | fps | 1101 | | iterations | 140 | | time_elapsed | 1041 | | total_timesteps | 1146880 | | train/ | | | approx_kl | 0.06612257 | | clip_fraction | 0.488 | | clip_range | 0.149 | | entropy_loss | -7.36 | | explained_variance | 0.498 | | learning_rate | 0.000247 | | loss | -0.0829 | | n_updates | 556 | | policy_gradient_loss | -0.0498 | | value_loss | 0.000677 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 239 | | ep_rew_mean | 0.243 | | time/ | | | fps | 1101 | | iterations | 141 | | time_elapsed | 1048 | | total_timesteps | 1155072 | | train/ | | | approx_kl | 0.069440186 | | clip_fraction | 0.488 | | clip_range | 0.149 | | entropy_loss | -7.4 | | explained_variance | 0.457 | | learning_rate | 0.000247 | | loss | -0.085 | | n_updates | 560 | | policy_gradient_loss | -0.0504 | | value_loss | 0.00073 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 234 | | ep_rew_mean | 0.23 | | time/ | | | fps | 1101 | | iterations | 142 | | time_elapsed | 1056 | | total_timesteps | 1163264 | | train/ | | | approx_kl | 0.06863488 | | clip_fraction | 0.485 | | clip_range | 0.149 | | entropy_loss | -7.35 | | explained_variance | 0.526 | | learning_rate | 0.000247 | | loss | -0.0759 | | n_updates | 564 | | policy_gradient_loss | -0.0502 | | value_loss | 0.000554 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 233 | | ep_rew_mean | 0.205 | | time/ | | | fps | 1101 | | iterations | 143 | | time_elapsed | 1063 | | total_timesteps | 1171456 | | train/ | | | approx_kl | 0.06616072 | | clip_fraction | 0.482 | | clip_range | 0.149 | | entropy_loss | -7.37 | | explained_variance | 0.518 | | learning_rate | 0.000247 | | loss | -0.0772 | | n_updates | 568 | | policy_gradient_loss | -0.0499 | | value_loss | 0.000596 | ---------------------------------------- --------------------------------------- | rollout/ | | | ep_len_mean | 237 | | ep_rew_mean | 0.226 | | time/ | | | fps | 1101 | | iterations | 144 | | time_elapsed | 1070 | | total_timesteps | 1179648 | | train/ | | | approx_kl | 0.0670695 | | clip_fraction | 0.49 | | clip_range | 0.149 | | entropy_loss | -7.35 | | explained_variance | 0.509 | | learning_rate | 0.000247 | | loss | -0.0777 | | n_updates | 572 | | policy_gradient_loss | -0.05 | | value_loss | 0.000626 | --------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 248 | | ep_rew_mean | 0.268 | | time/ | | | fps | 1101 | | iterations | 145 | | time_elapsed | 1078 | | total_timesteps | 1187840 | | train/ | | | approx_kl | 0.07294311 | | clip_fraction | 0.491 | | clip_range | 0.149 | | entropy_loss | -7.39 | | explained_variance | 0.555 | | learning_rate | 0.000247 | | loss | -0.0833 | | n_updates | 576 | | policy_gradient_loss | -0.0511 | | value_loss | 0.00059 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 248 | | ep_rew_mean | 0.274 | | time/ | | | fps | 1101 | | iterations | 146 | | time_elapsed | 1085 | | total_timesteps | 1196032 | | train/ | | | approx_kl | 0.07638498 | | clip_fraction | 0.492 | | clip_range | 0.149 | | entropy_loss | -7.39 | | explained_variance | 0.498 | | learning_rate | 0.000247 | | loss | -0.0836 | | n_updates | 580 | | policy_gradient_loss | -0.051 | | value_loss | 0.00069 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 242 | | ep_rew_mean | 0.267 | | time/ | | | fps | 1101 | | iterations | 147 | | time_elapsed | 1093 | | total_timesteps | 1204224 | | train/ | | | approx_kl | 0.065296106 | | clip_fraction | 0.491 | | clip_range | 0.149 | | entropy_loss | -7.38 | | explained_variance | 0.485 | | learning_rate | 0.000247 | | loss | -0.081 | | n_updates | 584 | | policy_gradient_loss | -0.0514 | | value_loss | 0.000653 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 242 | | ep_rew_mean | 0.242 | | time/ | | | fps | 1101 | | iterations | 148 | | time_elapsed | 1100 | | total_timesteps | 1212416 | | train/ | | | approx_kl | 0.069784686 | | clip_fraction | 0.486 | | clip_range | 0.148 | | entropy_loss | -7.41 | | explained_variance | 0.562 | | learning_rate | 0.000247 | | loss | -0.0777 | | n_updates | 588 | | policy_gradient_loss | -0.0496 | | value_loss | 0.000554 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 242 | | ep_rew_mean | 0.249 | | time/ | | | fps | 1101 | | iterations | 149 | | time_elapsed | 1108 | | total_timesteps | 1220608 | | train/ | | | approx_kl | 0.069644995 | | clip_fraction | 0.493 | | clip_range | 0.148 | | entropy_loss | -7.44 | | explained_variance | 0.528 | | learning_rate | 0.000247 | | loss | -0.0849 | | n_updates | 592 | | policy_gradient_loss | -0.0529 | | value_loss | 0.000601 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 251 | | ep_rew_mean | 0.264 | | time/ | | | fps | 1101 | | iterations | 150 | | time_elapsed | 1115 | | total_timesteps | 1228800 | | train/ | | | approx_kl | 0.06458496 | | clip_fraction | 0.474 | | clip_range | 0.148 | | entropy_loss | -7.42 | | explained_variance | 0.563 | | learning_rate | 0.000247 | | loss | -0.0852 | | n_updates | 596 | | policy_gradient_loss | -0.0478 | | value_loss | 0.000594 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 253 | | ep_rew_mean | 0.264 | | time/ | | | fps | 1101 | | iterations | 151 | | time_elapsed | 1123 | | total_timesteps | 1236992 | | train/ | | | approx_kl | 0.063582435 | | clip_fraction | 0.476 | | clip_range | 0.148 | | entropy_loss | -7.5 | | explained_variance | 0.478 | | learning_rate | 0.000247 | | loss | -0.0843 | | n_updates | 600 | | policy_gradient_loss | -0.0522 | | value_loss | 0.000626 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 245 | | ep_rew_mean | 0.257 | | time/ | | | fps | 1101 | | iterations | 152 | | time_elapsed | 1130 | | total_timesteps | 1245184 | | train/ | | | approx_kl | 0.06584619 | | clip_fraction | 0.485 | | clip_range | 0.148 | | entropy_loss | -7.45 | | explained_variance | 0.519 | | learning_rate | 0.000247 | | loss | -0.0879 | | n_updates | 604 | | policy_gradient_loss | -0.0528 | | value_loss | 0.000605 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 234 | | ep_rew_mean | 0.24 | | time/ | | | fps | 1101 | | iterations | 153 | | time_elapsed | 1138 | | total_timesteps | 1253376 | | train/ | | | approx_kl | 0.06833681 | | clip_fraction | 0.489 | | clip_range | 0.148 | | entropy_loss | -7.42 | | explained_variance | 0.521 | | learning_rate | 0.000247 | | loss | -0.0827 | | n_updates | 608 | | policy_gradient_loss | -0.0518 | | value_loss | 0.000663 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 237 | | ep_rew_mean | 0.232 | | time/ | | | fps | 1101 | | iterations | 154 | | time_elapsed | 1145 | | total_timesteps | 1261568 | | train/ | | | approx_kl | 0.06440784 | | clip_fraction | 0.474 | | clip_range | 0.148 | | entropy_loss | -7.41 | | explained_variance | 0.537 | | learning_rate | 0.000247 | | loss | -0.0784 | | n_updates | 612 | | policy_gradient_loss | -0.051 | | value_loss | 0.000569 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 244 | | ep_rew_mean | 0.24 | | time/ | | | fps | 1101 | | iterations | 155 | | time_elapsed | 1152 | | total_timesteps | 1269760 | | train/ | | | approx_kl | 0.06900003 | | clip_fraction | 0.483 | | clip_range | 0.148 | | entropy_loss | -7.44 | | explained_variance | 0.558 | | learning_rate | 0.000247 | | loss | -0.0829 | | n_updates | 616 | | policy_gradient_loss | -0.0532 | | value_loss | 0.000536 | ---------------------------------------- --------------------------------------- | rollout/ | | | ep_len_mean | 242 | | ep_rew_mean | 0.243 | | time/ | | | fps | 1101 | | iterations | 156 | | time_elapsed | 1160 | | total_timesteps | 1277952 | | train/ | | | approx_kl | 0.0679577 | | clip_fraction | 0.459 | | clip_range | 0.148 | | entropy_loss | -7.4 | | explained_variance | 0.526 | | learning_rate | 0.000247 | | loss | -0.0861 | | n_updates | 620 | | policy_gradient_loss | -0.051 | | value_loss | 0.000626 | --------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 239 | | ep_rew_mean | 0.268 | | time/ | | | fps | 1101 | | iterations | 157 | | time_elapsed | 1167 | | total_timesteps | 1286144 | | train/ | | | approx_kl | 0.06856276 | | clip_fraction | 0.476 | | clip_range | 0.148 | | entropy_loss | -7.42 | | explained_variance | 0.461 | | learning_rate | 0.000247 | | loss | -0.0855 | | n_updates | 624 | | policy_gradient_loss | -0.0533 | | value_loss | 0.000696 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 237 | | ep_rew_mean | 0.292 | | time/ | | | fps | 1101 | | iterations | 158 | | time_elapsed | 1174 | | total_timesteps | 1294336 | | train/ | | | approx_kl | 0.06775929 | | clip_fraction | 0.472 | | clip_range | 0.148 | | entropy_loss | -7.37 | | explained_variance | 0.494 | | learning_rate | 0.000247 | | loss | -0.0778 | | n_updates | 628 | | policy_gradient_loss | -0.0511 | | value_loss | 0.000695 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 242 | | ep_rew_mean | 0.311 | | time/ | | | fps | 1101 | | iterations | 159 | | time_elapsed | 1182 | | total_timesteps | 1302528 | | train/ | | | approx_kl | 0.06944973 | | clip_fraction | 0.481 | | clip_range | 0.148 | | entropy_loss | -7.37 | | explained_variance | 0.483 | | learning_rate | 0.000247 | | loss | -0.0822 | | n_updates | 632 | | policy_gradient_loss | -0.0514 | | value_loss | 0.000778 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 239 | | ep_rew_mean | 0.311 | | time/ | | | fps | 1102 | | iterations | 160 | | time_elapsed | 1189 | | total_timesteps | 1310720 | | train/ | | | approx_kl | 0.065226234 | | clip_fraction | 0.476 | | clip_range | 0.148 | | entropy_loss | -7.44 | | explained_variance | 0.466 | | learning_rate | 0.000247 | | loss | -0.092 | | n_updates | 636 | | policy_gradient_loss | -0.0553 | | value_loss | 0.000704 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 242 | | ep_rew_mean | 0.287 | | time/ | | | fps | 1102 | | iterations | 161 | | time_elapsed | 1196 | | total_timesteps | 1318912 | | train/ | | | approx_kl | 0.07137236 | | clip_fraction | 0.477 | | clip_range | 0.148 | | entropy_loss | -7.34 | | explained_variance | 0.507 | | learning_rate | 0.000247 | | loss | -0.0856 | | n_updates | 640 | | policy_gradient_loss | -0.0518 | | value_loss | 0.000724 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 234 | | ep_rew_mean | 0.255 | | time/ | | | fps | 1102 | | iterations | 162 | | time_elapsed | 1204 | | total_timesteps | 1327104 | | train/ | | | approx_kl | 0.067628235 | | clip_fraction | 0.476 | | clip_range | 0.148 | | entropy_loss | -7.38 | | explained_variance | 0.467 | | learning_rate | 0.000247 | | loss | -0.0807 | | n_updates | 644 | | policy_gradient_loss | -0.0491 | | value_loss | 0.000708 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 234 | | ep_rew_mean | 0.244 | | time/ | | | fps | 1101 | | iterations | 163 | | time_elapsed | 1211 | | total_timesteps | 1335296 | | train/ | | | approx_kl | 0.07429933 | | clip_fraction | 0.498 | | clip_range | 0.148 | | entropy_loss | -7.37 | | explained_variance | 0.526 | | learning_rate | 0.000247 | | loss | -0.0826 | | n_updates | 648 | | policy_gradient_loss | -0.0524 | | value_loss | 0.000659 | ---------------------------------------- --------------------------------------- | rollout/ | | | ep_len_mean | 231 | | ep_rew_mean | 0.241 | | time/ | | | fps | 1101 | | iterations | 164 | | time_elapsed | 1219 | | total_timesteps | 1343488 | | train/ | | | approx_kl | 0.0692776 | | clip_fraction | 0.487 | | clip_range | 0.148 | | entropy_loss | -7.4 | | explained_variance | 0.513 | | learning_rate | 0.000247 | | loss | -0.0835 | | n_updates | 652 | | policy_gradient_loss | -0.0509 | | value_loss | 0.000613 | --------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 240 | | ep_rew_mean | 0.241 | | time/ | | | fps | 1102 | | iterations | 165 | | time_elapsed | 1226 | | total_timesteps | 1351680 | | train/ | | | approx_kl | 0.075196624 | | clip_fraction | 0.478 | | clip_range | 0.148 | | entropy_loss | -7.38 | | explained_variance | 0.513 | | learning_rate | 0.000247 | | loss | -0.0857 | | n_updates | 656 | | policy_gradient_loss | -0.0513 | | value_loss | 0.000632 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 234 | | ep_rew_mean | 0.233 | | time/ | | | fps | 1102 | | iterations | 166 | | time_elapsed | 1233 | | total_timesteps | 1359872 | | train/ | | | approx_kl | 0.07038708 | | clip_fraction | 0.471 | | clip_range | 0.148 | | entropy_loss | -7.37 | | explained_variance | 0.577 | | learning_rate | 0.000247 | | loss | -0.0752 | | n_updates | 660 | | policy_gradient_loss | -0.0518 | | value_loss | 0.000527 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 232 | | ep_rew_mean | 0.249 | | time/ | | | fps | 1102 | | iterations | 167 | | time_elapsed | 1241 | | total_timesteps | 1368064 | | train/ | | | approx_kl | 0.07103458 | | clip_fraction | 0.475 | | clip_range | 0.148 | | entropy_loss | -7.31 | | explained_variance | 0.492 | | learning_rate | 0.000247 | | loss | -0.0775 | | n_updates | 664 | | policy_gradient_loss | -0.0504 | | value_loss | 0.000698 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 220 | | ep_rew_mean | 0.248 | | time/ | | | fps | 1102 | | iterations | 168 | | time_elapsed | 1248 | | total_timesteps | 1376256 | | train/ | | | approx_kl | 0.07026996 | | clip_fraction | 0.482 | | clip_range | 0.148 | | entropy_loss | -7.34 | | explained_variance | 0.505 | | learning_rate | 0.000247 | | loss | -0.0833 | | n_updates | 668 | | policy_gradient_loss | -0.0517 | | value_loss | 0.000684 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 225 | | ep_rew_mean | 0.254 | | time/ | | | fps | 1101 | | iterations | 169 | | time_elapsed | 1256 | | total_timesteps | 1384448 | | train/ | | | approx_kl | 0.07088623 | | clip_fraction | 0.491 | | clip_range | 0.148 | | entropy_loss | -7.3 | | explained_variance | 0.49 | | learning_rate | 0.000247 | | loss | -0.0831 | | n_updates | 672 | | policy_gradient_loss | -0.0529 | | value_loss | 0.000713 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 225 | | ep_rew_mean | 0.247 | | time/ | | | fps | 1102 | | iterations | 170 | | time_elapsed | 1263 | | total_timesteps | 1392640 | | train/ | | | approx_kl | 0.07031077 | | clip_fraction | 0.476 | | clip_range | 0.148 | | entropy_loss | -7.39 | | explained_variance | 0.462 | | learning_rate | 0.000247 | | loss | -0.0871 | | n_updates | 676 | | policy_gradient_loss | -0.0537 | | value_loss | 0.000661 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 232 | | ep_rew_mean | 0.281 | | time/ | | | fps | 1102 | | iterations | 171 | | time_elapsed | 1271 | | total_timesteps | 1400832 | | train/ | | | approx_kl | 0.069827735 | | clip_fraction | 0.481 | | clip_range | 0.148 | | entropy_loss | -7.34 | | explained_variance | 0.467 | | learning_rate | 0.000247 | | loss | -0.0843 | | n_updates | 680 | | policy_gradient_loss | -0.051 | | value_loss | 0.000794 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 228 | | ep_rew_mean | 0.283 | | time/ | | | fps | 1102 | | iterations | 172 | | time_elapsed | 1278 | | total_timesteps | 1409024 | | train/ | | | approx_kl | 0.06918645 | | clip_fraction | 0.49 | | clip_range | 0.148 | | entropy_loss | -7.34 | | explained_variance | 0.519 | | learning_rate | 0.000247 | | loss | -0.0802 | | n_updates | 684 | | policy_gradient_loss | -0.0537 | | value_loss | 0.000695 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 229 | | ep_rew_mean | 0.281 | | time/ | | | fps | 1102 | | iterations | 173 | | time_elapsed | 1285 | | total_timesteps | 1417216 | | train/ | | | approx_kl | 0.07108036 | | clip_fraction | 0.477 | | clip_range | 0.148 | | entropy_loss | -7.34 | | explained_variance | 0.541 | | learning_rate | 0.000247 | | loss | -0.0831 | | n_updates | 688 | | policy_gradient_loss | -0.0518 | | value_loss | 0.000718 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 233 | | ep_rew_mean | 0.272 | | time/ | | | fps | 1102 | | iterations | 174 | | time_elapsed | 1293 | | total_timesteps | 1425408 | | train/ | | | approx_kl | 0.07708906 | | clip_fraction | 0.493 | | clip_range | 0.148 | | entropy_loss | -7.35 | | explained_variance | 0.496 | | learning_rate | 0.000246 | | loss | -0.0849 | | n_updates | 692 | | policy_gradient_loss | -0.0521 | | value_loss | 0.000681 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 241 | | ep_rew_mean | 0.267 | | time/ | | | fps | 1102 | | iterations | 175 | | time_elapsed | 1300 | | total_timesteps | 1433600 | | train/ | | | approx_kl | 0.08033413 | | clip_fraction | 0.474 | | clip_range | 0.148 | | entropy_loss | -7.32 | | explained_variance | 0.541 | | learning_rate | 0.000246 | | loss | -0.0824 | | n_updates | 696 | | policy_gradient_loss | -0.0523 | | value_loss | 0.000622 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 240 | | ep_rew_mean | 0.295 | | time/ | | | fps | 1102 | | iterations | 176 | | time_elapsed | 1307 | | total_timesteps | 1441792 | | train/ | | | approx_kl | 0.07896854 | | clip_fraction | 0.498 | | clip_range | 0.148 | | entropy_loss | -7.29 | | explained_variance | 0.523 | | learning_rate | 0.000246 | | loss | -0.081 | | n_updates | 700 | | policy_gradient_loss | -0.054 | | value_loss | 0.000656 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 241 | | ep_rew_mean | 0.306 | | time/ | | | fps | 1102 | | iterations | 177 | | time_elapsed | 1315 | | total_timesteps | 1449984 | | train/ | | | approx_kl | 0.07502931 | | clip_fraction | 0.492 | | clip_range | 0.148 | | entropy_loss | -7.26 | | explained_variance | 0.54 | | learning_rate | 0.000246 | | loss | -0.0802 | | n_updates | 704 | | policy_gradient_loss | -0.0502 | | value_loss | 0.000696 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 237 | | ep_rew_mean | 0.319 | | time/ | | | fps | 1102 | | iterations | 178 | | time_elapsed | 1322 | | total_timesteps | 1458176 | | train/ | | | approx_kl | 0.08186533 | | clip_fraction | 0.49 | | clip_range | 0.148 | | entropy_loss | -7.3 | | explained_variance | 0.494 | | learning_rate | 0.000246 | | loss | -0.0805 | | n_updates | 708 | | policy_gradient_loss | -0.0546 | | value_loss | 0.000682 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 240 | | ep_rew_mean | 0.314 | | time/ | | | fps | 1102 | | iterations | 179 | | time_elapsed | 1330 | | total_timesteps | 1466368 | | train/ | | | approx_kl | 0.08714326 | | clip_fraction | 0.508 | | clip_range | 0.148 | | entropy_loss | -7.22 | | explained_variance | 0.501 | | learning_rate | 0.000246 | | loss | -0.0868 | | n_updates | 712 | | policy_gradient_loss | -0.0513 | | value_loss | 0.00078 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 235 | | ep_rew_mean | 0.293 | | time/ | | | fps | 1102 | | iterations | 180 | | time_elapsed | 1337 | | total_timesteps | 1474560 | | train/ | | | approx_kl | 0.07917763 | | clip_fraction | 0.495 | | clip_range | 0.148 | | entropy_loss | -7.2 | | explained_variance | 0.505 | | learning_rate | 0.000246 | | loss | -0.0833 | | n_updates | 716 | | policy_gradient_loss | -0.0526 | | value_loss | 0.000716 | ---------------------------------------- -------------------------------------- | rollout/ | | | ep_len_mean | 239 | | ep_rew_mean | 0.281 | | time/ | | | fps | 1102 | | iterations | 181 | | time_elapsed | 1345 | | total_timesteps | 1482752 | | train/ | | | approx_kl | 0.080517 | | clip_fraction | 0.503 | | clip_range | 0.148 | | entropy_loss | -7.22 | | explained_variance | 0.53 | | learning_rate | 0.000246 | | loss | -0.0825 | | n_updates | 720 | | policy_gradient_loss | -0.0532 | | value_loss | 0.000607 | -------------------------------------- --------------------------------------- | rollout/ | | | ep_len_mean | 236 | | ep_rew_mean | 0.284 | | time/ | | | fps | 1102 | | iterations | 182 | | time_elapsed | 1352 | | total_timesteps | 1490944 | | train/ | | | approx_kl | 0.0825504 | | clip_fraction | 0.499 | | clip_range | 0.148 | | entropy_loss | -7.25 | | explained_variance | 0.474 | | learning_rate | 0.000246 | | loss | -0.0777 | | n_updates | 724 | | policy_gradient_loss | -0.0525 | | value_loss | 0.000654 | --------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 231 | | ep_rew_mean | 0.295 | | time/ | | | fps | 1102 | | iterations | 183 | | time_elapsed | 1359 | | total_timesteps | 1499136 | | train/ | | | approx_kl | 0.07920864 | | clip_fraction | 0.505 | | clip_range | 0.148 | | entropy_loss | -7.24 | | explained_variance | 0.489 | | learning_rate | 0.000246 | | loss | -0.0724 | | n_updates | 728 | | policy_gradient_loss | -0.0491 | | value_loss | 0.000807 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 238 | | ep_rew_mean | 0.3 | | time/ | | | fps | 1102 | | iterations | 184 | | time_elapsed | 1367 | | total_timesteps | 1507328 | | train/ | | | approx_kl | 0.08776355 | | clip_fraction | 0.492 | | clip_range | 0.148 | | entropy_loss | -7.25 | | explained_variance | 0.468 | | learning_rate | 0.000246 | | loss | -0.0812 | | n_updates | 732 | | policy_gradient_loss | -0.0536 | | value_loss | 0.000796 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 239 | | ep_rew_mean | 0.276 | | time/ | | | fps | 1102 | | iterations | 185 | | time_elapsed | 1374 | | total_timesteps | 1515520 | | train/ | | | approx_kl | 0.08111123 | | clip_fraction | 0.496 | | clip_range | 0.148 | | entropy_loss | -7.32 | | explained_variance | 0.491 | | learning_rate | 0.000246 | | loss | -0.0815 | | n_updates | 736 | | policy_gradient_loss | -0.0535 | | value_loss | 0.00062 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 248 | | ep_rew_mean | 0.291 | | time/ | | | fps | 1102 | | iterations | 186 | | time_elapsed | 1381 | | total_timesteps | 1523712 | | train/ | | | approx_kl | 0.085650064 | | clip_fraction | 0.498 | | clip_range | 0.148 | | entropy_loss | -7.29 | | explained_variance | 0.527 | | learning_rate | 0.000246 | | loss | -0.0878 | | n_updates | 740 | | policy_gradient_loss | -0.0539 | | value_loss | 0.000717 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 240 | | ep_rew_mean | 0.274 | | time/ | | | fps | 1102 | | iterations | 187 | | time_elapsed | 1389 | | total_timesteps | 1531904 | | train/ | | | approx_kl | 0.08082384 | | clip_fraction | 0.501 | | clip_range | 0.148 | | entropy_loss | -7.36 | | explained_variance | 0.523 | | learning_rate | 0.000246 | | loss | -0.0867 | | n_updates | 744 | | policy_gradient_loss | -0.0506 | | value_loss | 0.000653 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 249 | | ep_rew_mean | 0.291 | | time/ | | | fps | 1103 | | iterations | 188 | | time_elapsed | 1396 | | total_timesteps | 1540096 | | train/ | | | approx_kl | 0.08884859 | | clip_fraction | 0.501 | | clip_range | 0.148 | | entropy_loss | -7.32 | | explained_variance | 0.578 | | learning_rate | 0.000246 | | loss | -0.0798 | | n_updates | 748 | | policy_gradient_loss | -0.0545 | | value_loss | 0.000621 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 250 | | ep_rew_mean | 0.282 | | time/ | | | fps | 1103 | | iterations | 189 | | time_elapsed | 1403 | | total_timesteps | 1548288 | | train/ | | | approx_kl | 0.08770391 | | clip_fraction | 0.496 | | clip_range | 0.148 | | entropy_loss | -7.37 | | explained_variance | 0.527 | | learning_rate | 0.000246 | | loss | -0.0893 | | n_updates | 752 | | policy_gradient_loss | -0.055 | | value_loss | 0.000599 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 254 | | ep_rew_mean | 0.283 | | time/ | | | fps | 1103 | | iterations | 190 | | time_elapsed | 1410 | | total_timesteps | 1556480 | | train/ | | | approx_kl | 0.083978266 | | clip_fraction | 0.504 | | clip_range | 0.148 | | entropy_loss | -7.31 | | explained_variance | 0.494 | | learning_rate | 0.000246 | | loss | -0.0873 | | n_updates | 756 | | policy_gradient_loss | -0.0519 | | value_loss | 0.000644 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 249 | | ep_rew_mean | 0.278 | | time/ | | | fps | 1103 | | iterations | 191 | | time_elapsed | 1417 | | total_timesteps | 1564672 | | train/ | | | approx_kl | 0.079572804 | | clip_fraction | 0.496 | | clip_range | 0.148 | | entropy_loss | -7.31 | | explained_variance | 0.572 | | learning_rate | 0.000246 | | loss | -0.0848 | | n_updates | 760 | | policy_gradient_loss | -0.0539 | | value_loss | 0.000555 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 249 | | ep_rew_mean | 0.277 | | time/ | | | fps | 1103 | | iterations | 192 | | time_elapsed | 1425 | | total_timesteps | 1572864 | | train/ | | | approx_kl | 0.08504398 | | clip_fraction | 0.501 | | clip_range | 0.148 | | entropy_loss | -7.3 | | explained_variance | 0.539 | | learning_rate | 0.000246 | | loss | -0.0821 | | n_updates | 764 | | policy_gradient_loss | -0.0515 | | value_loss | 0.000653 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 242 | | ep_rew_mean | 0.278 | | time/ | | | fps | 1103 | | iterations | 193 | | time_elapsed | 1432 | | total_timesteps | 1581056 | | train/ | | | approx_kl | 0.085106105 | | clip_fraction | 0.504 | | clip_range | 0.148 | | entropy_loss | -7.33 | | explained_variance | 0.482 | | learning_rate | 0.000246 | | loss | -0.0858 | | n_updates | 768 | | policy_gradient_loss | -0.0521 | | value_loss | 0.00065 | ----------------------------------------- --------------------------------------- | rollout/ | | | ep_len_mean | 234 | | ep_rew_mean | 0.27 | | time/ | | | fps | 1103 | | iterations | 194 | | time_elapsed | 1440 | | total_timesteps | 1589248 | | train/ | | | approx_kl | 0.0826439 | | clip_fraction | 0.502 | | clip_range | 0.148 | | entropy_loss | -7.29 | | explained_variance | 0.54 | | learning_rate | 0.000246 | | loss | -0.0848 | | n_updates | 772 | | policy_gradient_loss | -0.0525 | | value_loss | 0.000647 | --------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 229 | | ep_rew_mean | 0.265 | | time/ | | | fps | 1103 | | iterations | 195 | | time_elapsed | 1447 | | total_timesteps | 1597440 | | train/ | | | approx_kl | 0.08335239 | | clip_fraction | 0.494 | | clip_range | 0.148 | | entropy_loss | -7.3 | | explained_variance | 0.486 | | learning_rate | 0.000246 | | loss | -0.0819 | | n_updates | 776 | | policy_gradient_loss | -0.0544 | | value_loss | 0.000715 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 238 | | ep_rew_mean | 0.281 | | time/ | | | fps | 1103 | | iterations | 196 | | time_elapsed | 1454 | | total_timesteps | 1605632 | | train/ | | | approx_kl | 0.081063315 | | clip_fraction | 0.483 | | clip_range | 0.148 | | entropy_loss | -7.24 | | explained_variance | 0.522 | | learning_rate | 0.000246 | | loss | -0.0847 | | n_updates | 780 | | policy_gradient_loss | -0.0528 | | value_loss | 0.000673 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 241 | | ep_rew_mean | 0.284 | | time/ | | | fps | 1103 | | iterations | 197 | | time_elapsed | 1462 | | total_timesteps | 1613824 | | train/ | | | approx_kl | 0.07722767 | | clip_fraction | 0.491 | | clip_range | 0.148 | | entropy_loss | -7.29 | | explained_variance | 0.528 | | learning_rate | 0.000246 | | loss | -0.0865 | | n_updates | 784 | | policy_gradient_loss | -0.0538 | | value_loss | 0.000592 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 249 | | ep_rew_mean | 0.283 | | time/ | | | fps | 1103 | | iterations | 198 | | time_elapsed | 1469 | | total_timesteps | 1622016 | | train/ | | | approx_kl | 0.07998459 | | clip_fraction | 0.505 | | clip_range | 0.148 | | entropy_loss | -7.22 | | explained_variance | 0.497 | | learning_rate | 0.000246 | | loss | -0.0833 | | n_updates | 788 | | policy_gradient_loss | -0.0538 | | value_loss | 0.000727 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 245 | | ep_rew_mean | 0.272 | | time/ | | | fps | 1103 | | iterations | 199 | | time_elapsed | 1477 | | total_timesteps | 1630208 | | train/ | | | approx_kl | 0.084796876 | | clip_fraction | 0.503 | | clip_range | 0.148 | | entropy_loss | -7.23 | | explained_variance | 0.563 | | learning_rate | 0.000246 | | loss | -0.0848 | | n_updates | 792 | | policy_gradient_loss | -0.0541 | | value_loss | 0.000575 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 246 | | ep_rew_mean | 0.302 | | time/ | | | fps | 1103 | | iterations | 200 | | time_elapsed | 1484 | | total_timesteps | 1638400 | | train/ | | | approx_kl | 0.08930965 | | clip_fraction | 0.517 | | clip_range | 0.148 | | entropy_loss | -7.24 | | explained_variance | 0.572 | | learning_rate | 0.000246 | | loss | -0.0881 | | n_updates | 796 | | policy_gradient_loss | -0.0535 | | value_loss | 0.000577 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 245 | | ep_rew_mean | 0.322 | | time/ | | | fps | 1103 | | iterations | 201 | | time_elapsed | 1492 | | total_timesteps | 1646592 | | train/ | | | approx_kl | 0.08401638 | | clip_fraction | 0.511 | | clip_range | 0.148 | | entropy_loss | -7.22 | | explained_variance | 0.503 | | learning_rate | 0.000246 | | loss | -0.087 | | n_updates | 800 | | policy_gradient_loss | -0.0544 | | value_loss | 0.000742 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 243 | | ep_rew_mean | 0.337 | | time/ | | | fps | 1103 | | iterations | 202 | | time_elapsed | 1499 | | total_timesteps | 1654784 | | train/ | | | approx_kl | 0.09070188 | | clip_fraction | 0.511 | | clip_range | 0.148 | | entropy_loss | -7.16 | | explained_variance | 0.512 | | learning_rate | 0.000246 | | loss | -0.0904 | | n_updates | 804 | | policy_gradient_loss | -0.0543 | | value_loss | 0.000733 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 244 | | ep_rew_mean | 0.325 | | time/ | | | fps | 1103 | | iterations | 203 | | time_elapsed | 1506 | | total_timesteps | 1662976 | | train/ | | | approx_kl | 0.098129004 | | clip_fraction | 0.519 | | clip_range | 0.148 | | entropy_loss | -7.16 | | explained_variance | 0.456 | | learning_rate | 0.000246 | | loss | -0.0852 | | n_updates | 808 | | policy_gradient_loss | -0.0559 | | value_loss | 0.000683 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 237 | | ep_rew_mean | 0.315 | | time/ | | | fps | 1103 | | iterations | 204 | | time_elapsed | 1514 | | total_timesteps | 1671168 | | train/ | | | approx_kl | 0.09626436 | | clip_fraction | 0.52 | | clip_range | 0.148 | | entropy_loss | -7.13 | | explained_variance | 0.553 | | learning_rate | 0.000246 | | loss | -0.0847 | | n_updates | 812 | | policy_gradient_loss | -0.0532 | | value_loss | 0.000656 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 239 | | ep_rew_mean | 0.301 | | time/ | | | fps | 1103 | | iterations | 205 | | time_elapsed | 1521 | | total_timesteps | 1679360 | | train/ | | | approx_kl | 0.09632793 | | clip_fraction | 0.506 | | clip_range | 0.148 | | entropy_loss | -7.13 | | explained_variance | 0.505 | | learning_rate | 0.000246 | | loss | -0.0839 | | n_updates | 816 | | policy_gradient_loss | -0.0525 | | value_loss | 0.000782 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 232 | | ep_rew_mean | 0.258 | | time/ | | | fps | 1103 | | iterations | 206 | | time_elapsed | 1529 | | total_timesteps | 1687552 | | train/ | | | approx_kl | 0.10363456 | | clip_fraction | 0.517 | | clip_range | 0.148 | | entropy_loss | -7.15 | | explained_variance | 0.568 | | learning_rate | 0.000246 | | loss | -0.0799 | | n_updates | 820 | | policy_gradient_loss | -0.0528 | | value_loss | 0.000572 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 228 | | ep_rew_mean | 0.268 | | time/ | | | fps | 1103 | | iterations | 207 | | time_elapsed | 1536 | | total_timesteps | 1695744 | | train/ | | | approx_kl | 0.08010447 | | clip_fraction | 0.494 | | clip_range | 0.148 | | entropy_loss | -7.18 | | explained_variance | 0.595 | | learning_rate | 0.000246 | | loss | -0.0817 | | n_updates | 824 | | policy_gradient_loss | -0.052 | | value_loss | 0.000584 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 230 | | ep_rew_mean | 0.272 | | time/ | | | fps | 1103 | | iterations | 208 | | time_elapsed | 1543 | | total_timesteps | 1703936 | | train/ | | | approx_kl | 0.08379765 | | clip_fraction | 0.498 | | clip_range | 0.148 | | entropy_loss | -7.14 | | explained_variance | 0.535 | | learning_rate | 0.000246 | | loss | -0.0845 | | n_updates | 828 | | policy_gradient_loss | -0.0533 | | value_loss | 0.000772 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 228 | | ep_rew_mean | 0.272 | | time/ | | | fps | 1104 | | iterations | 209 | | time_elapsed | 1550 | | total_timesteps | 1712128 | | train/ | | | approx_kl | 0.084038556 | | clip_fraction | 0.495 | | clip_range | 0.148 | | entropy_loss | -7.2 | | explained_variance | 0.611 | | learning_rate | 0.000246 | | loss | -0.0856 | | n_updates | 832 | | policy_gradient_loss | -0.0535 | | value_loss | 0.000571 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 225 | | ep_rew_mean | 0.274 | | time/ | | | fps | 1104 | | iterations | 210 | | time_elapsed | 1557 | | total_timesteps | 1720320 | | train/ | | | approx_kl | 0.08232991 | | clip_fraction | 0.489 | | clip_range | 0.148 | | entropy_loss | -7.18 | | explained_variance | 0.494 | | learning_rate | 0.000246 | | loss | -0.0902 | | n_updates | 836 | | policy_gradient_loss | -0.0537 | | value_loss | 0.000725 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 227 | | ep_rew_mean | 0.289 | | time/ | | | fps | 1104 | | iterations | 211 | | time_elapsed | 1564 | | total_timesteps | 1728512 | | train/ | | | approx_kl | 0.090407774 | | clip_fraction | 0.501 | | clip_range | 0.148 | | entropy_loss | -7.17 | | explained_variance | 0.538 | | learning_rate | 0.000246 | | loss | -0.0869 | | n_updates | 840 | | policy_gradient_loss | -0.0516 | | value_loss | 0.000716 | ----------------------------------------- --------------------------------------- | rollout/ | | | ep_len_mean | 233 | | ep_rew_mean | 0.316 | | time/ | | | fps | 1104 | | iterations | 212 | | time_elapsed | 1571 | | total_timesteps | 1736704 | | train/ | | | approx_kl | 0.0919661 | | clip_fraction | 0.509 | | clip_range | 0.148 | | entropy_loss | -7.11 | | explained_variance | 0.523 | | learning_rate | 0.000246 | | loss | -0.0711 | | n_updates | 844 | | policy_gradient_loss | -0.0529 | | value_loss | 0.000704 | --------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 242 | | ep_rew_mean | 0.315 | | time/ | | | fps | 1105 | | iterations | 213 | | time_elapsed | 1578 | | total_timesteps | 1744896 | | train/ | | | approx_kl | 0.09922445 | | clip_fraction | 0.513 | | clip_range | 0.148 | | entropy_loss | -7.16 | | explained_variance | 0.486 | | learning_rate | 0.000246 | | loss | -0.0795 | | n_updates | 848 | | policy_gradient_loss | -0.054 | | value_loss | 0.000737 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 241 | | ep_rew_mean | 0.309 | | time/ | | | fps | 1105 | | iterations | 214 | | time_elapsed | 1585 | | total_timesteps | 1753088 | | train/ | | | approx_kl | 0.088032275 | | clip_fraction | 0.496 | | clip_range | 0.148 | | entropy_loss | -7.1 | | explained_variance | 0.493 | | learning_rate | 0.000246 | | loss | -0.0836 | | n_updates | 852 | | policy_gradient_loss | -0.0528 | | value_loss | 0.00075 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 237 | | ep_rew_mean | 0.284 | | time/ | | | fps | 1105 | | iterations | 215 | | time_elapsed | 1592 | | total_timesteps | 1761280 | | train/ | | | approx_kl | 0.08731289 | | clip_fraction | 0.507 | | clip_range | 0.148 | | entropy_loss | -7.1 | | explained_variance | 0.591 | | learning_rate | 0.000246 | | loss | -0.0829 | | n_updates | 856 | | policy_gradient_loss | -0.0537 | | value_loss | 0.000611 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 233 | | ep_rew_mean | 0.294 | | time/ | | | fps | 1106 | | iterations | 216 | | time_elapsed | 1599 | | total_timesteps | 1769472 | | train/ | | | approx_kl | 0.08080551 | | clip_fraction | 0.498 | | clip_range | 0.148 | | entropy_loss | -7.1 | | explained_variance | 0.606 | | learning_rate | 0.000246 | | loss | -0.0867 | | n_updates | 860 | | policy_gradient_loss | -0.0514 | | value_loss | 0.000594 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 230 | | ep_rew_mean | 0.297 | | time/ | | | fps | 1106 | | iterations | 217 | | time_elapsed | 1607 | | total_timesteps | 1777664 | | train/ | | | approx_kl | 0.09105197 | | clip_fraction | 0.51 | | clip_range | 0.148 | | entropy_loss | -7.06 | | explained_variance | 0.555 | | learning_rate | 0.000246 | | loss | -0.0835 | | n_updates | 864 | | policy_gradient_loss | -0.0519 | | value_loss | 0.000714 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 236 | | ep_rew_mean | 0.29 | | time/ | | | fps | 1106 | | iterations | 218 | | time_elapsed | 1614 | | total_timesteps | 1785856 | | train/ | | | approx_kl | 0.09286306 | | clip_fraction | 0.505 | | clip_range | 0.148 | | entropy_loss | -7.14 | | explained_variance | 0.558 | | learning_rate | 0.000246 | | loss | -0.0943 | | n_updates | 868 | | policy_gradient_loss | -0.0558 | | value_loss | 0.000638 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 238 | | ep_rew_mean | 0.281 | | time/ | | | fps | 1106 | | iterations | 219 | | time_elapsed | 1621 | | total_timesteps | 1794048 | | train/ | | | approx_kl | 0.08781908 | | clip_fraction | 0.497 | | clip_range | 0.148 | | entropy_loss | -7.15 | | explained_variance | 0.579 | | learning_rate | 0.000246 | | loss | -0.078 | | n_updates | 872 | | policy_gradient_loss | -0.0526 | | value_loss | 0.000587 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 233 | | ep_rew_mean | 0.298 | | time/ | | | fps | 1106 | | iterations | 220 | | time_elapsed | 1628 | | total_timesteps | 1802240 | | train/ | | | approx_kl | 0.08710103 | | clip_fraction | 0.489 | | clip_range | 0.148 | | entropy_loss | -7.14 | | explained_variance | 0.602 | | learning_rate | 0.000246 | | loss | -0.0747 | | n_updates | 876 | | policy_gradient_loss | -0.0515 | | value_loss | 0.000608 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 221 | | ep_rew_mean | 0.308 | | time/ | | | fps | 1106 | | iterations | 221 | | time_elapsed | 1636 | | total_timesteps | 1810432 | | train/ | | | approx_kl | 0.09429751 | | clip_fraction | 0.517 | | clip_range | 0.148 | | entropy_loss | -7.02 | | explained_variance | 0.52 | | learning_rate | 0.000246 | | loss | -0.0814 | | n_updates | 880 | | policy_gradient_loss | -0.0508 | | value_loss | 0.000796 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 226 | | ep_rew_mean | 0.326 | | time/ | | | fps | 1106 | | iterations | 222 | | time_elapsed | 1643 | | total_timesteps | 1818624 | | train/ | | | approx_kl | 0.092921875 | | clip_fraction | 0.51 | | clip_range | 0.148 | | entropy_loss | -7.1 | | explained_variance | 0.501 | | learning_rate | 0.000246 | | loss | -0.0872 | | n_updates | 884 | | policy_gradient_loss | -0.0529 | | value_loss | 0.000729 | ----------------------------------------- --------------------------------------- | rollout/ | | | ep_len_mean | 233 | | ep_rew_mean | 0.306 | | time/ | | | fps | 1106 | | iterations | 223 | | time_elapsed | 1650 | | total_timesteps | 1826816 | | train/ | | | approx_kl | 0.0943868 | | clip_fraction | 0.514 | | clip_range | 0.148 | | entropy_loss | -7.06 | | explained_variance | 0.589 | | learning_rate | 0.000245 | | loss | -0.0838 | | n_updates | 888 | | policy_gradient_loss | -0.0536 | | value_loss | 0.000596 | --------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 238 | | ep_rew_mean | 0.31 | | time/ | | | fps | 1106 | | iterations | 224 | | time_elapsed | 1658 | | total_timesteps | 1835008 | | train/ | | | approx_kl | 0.101720184 | | clip_fraction | 0.519 | | clip_range | 0.148 | | entropy_loss | -7.09 | | explained_variance | 0.601 | | learning_rate | 0.000245 | | loss | -0.088 | | n_updates | 892 | | policy_gradient_loss | -0.0543 | | value_loss | 0.000597 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 237 | | ep_rew_mean | 0.302 | | time/ | | | fps | 1106 | | iterations | 225 | | time_elapsed | 1665 | | total_timesteps | 1843200 | | train/ | | | approx_kl | 0.094355926 | | clip_fraction | 0.499 | | clip_range | 0.148 | | entropy_loss | -7.06 | | explained_variance | 0.567 | | learning_rate | 0.000245 | | loss | -0.0839 | | n_updates | 896 | | policy_gradient_loss | -0.0538 | | value_loss | 0.000641 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 245 | | ep_rew_mean | 0.3 | | time/ | | | fps | 1106 | | iterations | 226 | | time_elapsed | 1672 | | total_timesteps | 1851392 | | train/ | | | approx_kl | 0.10181391 | | clip_fraction | 0.502 | | clip_range | 0.148 | | entropy_loss | -7.07 | | explained_variance | 0.557 | | learning_rate | 0.000245 | | loss | -0.0807 | | n_updates | 900 | | policy_gradient_loss | -0.0547 | | value_loss | 0.000658 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 241 | | ep_rew_mean | 0.306 | | time/ | | | fps | 1107 | | iterations | 227 | | time_elapsed | 1679 | | total_timesteps | 1859584 | | train/ | | | approx_kl | 0.108819306 | | clip_fraction | 0.524 | | clip_range | 0.148 | | entropy_loss | -7.06 | | explained_variance | 0.602 | | learning_rate | 0.000245 | | loss | -0.0795 | | n_updates | 904 | | policy_gradient_loss | -0.0548 | | value_loss | 0.000544 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 243 | | ep_rew_mean | 0.313 | | time/ | | | fps | 1107 | | iterations | 228 | | time_elapsed | 1686 | | total_timesteps | 1867776 | | train/ | | | approx_kl | 0.106578164 | | clip_fraction | 0.526 | | clip_range | 0.148 | | entropy_loss | -6.96 | | explained_variance | 0.52 | | learning_rate | 0.000245 | | loss | -0.0898 | | n_updates | 908 | | policy_gradient_loss | -0.0534 | | value_loss | 0.00073 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 238 | | ep_rew_mean | 0.33 | | time/ | | | fps | 1107 | | iterations | 229 | | time_elapsed | 1694 | | total_timesteps | 1875968 | | train/ | | | approx_kl | 0.10179232 | | clip_fraction | 0.525 | | clip_range | 0.148 | | entropy_loss | -6.91 | | explained_variance | 0.538 | | learning_rate | 0.000245 | | loss | -0.0812 | | n_updates | 912 | | policy_gradient_loss | -0.054 | | value_loss | 0.000702 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 236 | | ep_rew_mean | 0.326 | | time/ | | | fps | 1107 | | iterations | 230 | | time_elapsed | 1701 | | total_timesteps | 1884160 | | train/ | | | approx_kl | 0.107317895 | | clip_fraction | 0.536 | | clip_range | 0.148 | | entropy_loss | -6.94 | | explained_variance | 0.571 | | learning_rate | 0.000245 | | loss | -0.0896 | | n_updates | 916 | | policy_gradient_loss | -0.0537 | | value_loss | 0.000591 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 243 | | ep_rew_mean | 0.328 | | time/ | | | fps | 1107 | | iterations | 231 | | time_elapsed | 1708 | | total_timesteps | 1892352 | | train/ | | | approx_kl | 0.11547114 | | clip_fraction | 0.516 | | clip_range | 0.148 | | entropy_loss | -6.91 | | explained_variance | 0.493 | | learning_rate | 0.000245 | | loss | -0.082 | | n_updates | 920 | | policy_gradient_loss | -0.053 | | value_loss | 0.00078 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 235 | | ep_rew_mean | 0.317 | | time/ | | | fps | 1107 | | iterations | 232 | | time_elapsed | 1715 | | total_timesteps | 1900544 | | train/ | | | approx_kl | 0.10672625 | | clip_fraction | 0.524 | | clip_range | 0.148 | | entropy_loss | -6.9 | | explained_variance | 0.553 | | learning_rate | 0.000245 | | loss | -0.0823 | | n_updates | 924 | | policy_gradient_loss | -0.053 | | value_loss | 0.000671 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 238 | | ep_rew_mean | 0.329 | | time/ | | | fps | 1107 | | iterations | 233 | | time_elapsed | 1722 | | total_timesteps | 1908736 | | train/ | | | approx_kl | 0.110047564 | | clip_fraction | 0.52 | | clip_range | 0.148 | | entropy_loss | -6.84 | | explained_variance | 0.569 | | learning_rate | 0.000245 | | loss | -0.085 | | n_updates | 928 | | policy_gradient_loss | -0.0535 | | value_loss | 0.000671 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 229 | | ep_rew_mean | 0.341 | | time/ | | | fps | 1107 | | iterations | 234 | | time_elapsed | 1730 | | total_timesteps | 1916928 | | train/ | | | approx_kl | 0.10164595 | | clip_fraction | 0.518 | | clip_range | 0.148 | | entropy_loss | -6.82 | | explained_variance | 0.559 | | learning_rate | 0.000245 | | loss | -0.0818 | | n_updates | 932 | | policy_gradient_loss | -0.0522 | | value_loss | 0.000761 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 230 | | ep_rew_mean | 0.363 | | time/ | | | fps | 1108 | | iterations | 235 | | time_elapsed | 1737 | | total_timesteps | 1925120 | | train/ | | | approx_kl | 0.10495236 | | clip_fraction | 0.52 | | clip_range | 0.148 | | entropy_loss | -6.84 | | explained_variance | 0.554 | | learning_rate | 0.000245 | | loss | -0.0819 | | n_updates | 936 | | policy_gradient_loss | -0.052 | | value_loss | 0.000708 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 235 | | ep_rew_mean | 0.367 | | time/ | | | fps | 1108 | | iterations | 236 | | time_elapsed | 1744 | | total_timesteps | 1933312 | | train/ | | | approx_kl | 0.10555805 | | clip_fraction | 0.53 | | clip_range | 0.148 | | entropy_loss | -6.77 | | explained_variance | 0.496 | | learning_rate | 0.000245 | | loss | -0.0833 | | n_updates | 940 | | policy_gradient_loss | -0.0521 | | value_loss | 0.000913 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 241 | | ep_rew_mean | 0.34 | | time/ | | | fps | 1108 | | iterations | 237 | | time_elapsed | 1751 | | total_timesteps | 1941504 | | train/ | | | approx_kl | 0.10862024 | | clip_fraction | 0.523 | | clip_range | 0.148 | | entropy_loss | -6.76 | | explained_variance | 0.472 | | learning_rate | 0.000245 | | loss | -0.0828 | | n_updates | 944 | | policy_gradient_loss | -0.0519 | | value_loss | 0.00082 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 236 | | ep_rew_mean | 0.337 | | time/ | | | fps | 1108 | | iterations | 238 | | time_elapsed | 1759 | | total_timesteps | 1949696 | | train/ | | | approx_kl | 0.11077298 | | clip_fraction | 0.521 | | clip_range | 0.148 | | entropy_loss | -6.77 | | explained_variance | 0.546 | | learning_rate | 0.000245 | | loss | -0.0853 | | n_updates | 948 | | policy_gradient_loss | -0.0534 | | value_loss | 0.000666 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 240 | | ep_rew_mean | 0.32 | | time/ | | | fps | 1108 | | iterations | 239 | | time_elapsed | 1766 | | total_timesteps | 1957888 | | train/ | | | approx_kl | 0.10972123 | | clip_fraction | 0.517 | | clip_range | 0.148 | | entropy_loss | -6.79 | | explained_variance | 0.576 | | learning_rate | 0.000245 | | loss | -0.0837 | | n_updates | 952 | | policy_gradient_loss | -0.053 | | value_loss | 0.000693 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 245 | | ep_rew_mean | 0.345 | | time/ | | | fps | 1108 | | iterations | 240 | | time_elapsed | 1773 | | total_timesteps | 1966080 | | train/ | | | approx_kl | 0.11470166 | | clip_fraction | 0.515 | | clip_range | 0.148 | | entropy_loss | -6.81 | | explained_variance | 0.538 | | learning_rate | 0.000245 | | loss | -0.0831 | | n_updates | 956 | | policy_gradient_loss | -0.0527 | | value_loss | 0.000701 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 251 | | ep_rew_mean | 0.354 | | time/ | | | fps | 1108 | | iterations | 241 | | time_elapsed | 1781 | | total_timesteps | 1974272 | | train/ | | | approx_kl | 0.11648223 | | clip_fraction | 0.534 | | clip_range | 0.148 | | entropy_loss | -6.74 | | explained_variance | 0.602 | | learning_rate | 0.000245 | | loss | -0.0903 | | n_updates | 960 | | policy_gradient_loss | -0.0544 | | value_loss | 0.000577 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 246 | | ep_rew_mean | 0.363 | | time/ | | | fps | 1108 | | iterations | 242 | | time_elapsed | 1788 | | total_timesteps | 1982464 | | train/ | | | approx_kl | 0.10504311 | | clip_fraction | 0.521 | | clip_range | 0.148 | | entropy_loss | -6.7 | | explained_variance | 0.522 | | learning_rate | 0.000245 | | loss | -0.0796 | | n_updates | 964 | | policy_gradient_loss | -0.0522 | | value_loss | 0.000778 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 239 | | ep_rew_mean | 0.357 | | time/ | | | fps | 1108 | | iterations | 243 | | time_elapsed | 1795 | | total_timesteps | 1990656 | | train/ | | | approx_kl | 0.12133829 | | clip_fraction | 0.528 | | clip_range | 0.148 | | entropy_loss | -6.73 | | explained_variance | 0.528 | | learning_rate | 0.000245 | | loss | -0.085 | | n_updates | 968 | | policy_gradient_loss | -0.0512 | | value_loss | 0.00075 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 240 | | ep_rew_mean | 0.35 | | time/ | | | fps | 1108 | | iterations | 244 | | time_elapsed | 1802 | | total_timesteps | 1998848 | | train/ | | | approx_kl | 0.12634405 | | clip_fraction | 0.527 | | clip_range | 0.148 | | entropy_loss | -6.77 | | explained_variance | 0.565 | | learning_rate | 0.000245 | | loss | -0.0839 | | n_updates | 972 | | policy_gradient_loss | -0.0533 | | value_loss | 0.000669 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 243 | | ep_rew_mean | 0.356 | | time/ | | | fps | 1108 | | iterations | 245 | | time_elapsed | 1810 | | total_timesteps | 2007040 | | train/ | | | approx_kl | 0.10862511 | | clip_fraction | 0.521 | | clip_range | 0.148 | | entropy_loss | -6.74 | | explained_variance | 0.563 | | learning_rate | 0.000245 | | loss | -0.0893 | | n_updates | 976 | | policy_gradient_loss | -0.054 | | value_loss | 0.000653 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 239 | | ep_rew_mean | 0.346 | | time/ | | | fps | 1108 | | iterations | 246 | | time_elapsed | 1817 | | total_timesteps | 2015232 | | train/ | | | approx_kl | 0.11088178 | | clip_fraction | 0.523 | | clip_range | 0.147 | | entropy_loss | -6.73 | | explained_variance | 0.544 | | learning_rate | 0.000245 | | loss | -0.0793 | | n_updates | 980 | | policy_gradient_loss | -0.0515 | | value_loss | 0.000754 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 238 | | ep_rew_mean | 0.331 | | time/ | | | fps | 1109 | | iterations | 247 | | time_elapsed | 1824 | | total_timesteps | 2023424 | | train/ | | | approx_kl | 0.12056622 | | clip_fraction | 0.521 | | clip_range | 0.147 | | entropy_loss | -6.68 | | explained_variance | 0.584 | | learning_rate | 0.000245 | | loss | -0.0903 | | n_updates | 984 | | policy_gradient_loss | -0.0549 | | value_loss | 0.000677 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 241 | | ep_rew_mean | 0.337 | | time/ | | | fps | 1109 | | iterations | 248 | | time_elapsed | 1831 | | total_timesteps | 2031616 | | train/ | | | approx_kl | 0.114841856 | | clip_fraction | 0.52 | | clip_range | 0.147 | | entropy_loss | -6.7 | | explained_variance | 0.54 | | learning_rate | 0.000245 | | loss | -0.0859 | | n_updates | 988 | | policy_gradient_loss | -0.0523 | | value_loss | 0.000734 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 240 | | ep_rew_mean | 0.342 | | time/ | | | fps | 1109 | | iterations | 249 | | time_elapsed | 1838 | | total_timesteps | 2039808 | | train/ | | | approx_kl | 0.09891673 | | clip_fraction | 0.518 | | clip_range | 0.147 | | entropy_loss | -6.7 | | explained_variance | 0.56 | | learning_rate | 0.000245 | | loss | -0.0801 | | n_updates | 992 | | policy_gradient_loss | -0.0497 | | value_loss | 0.000706 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 243 | | ep_rew_mean | 0.349 | | time/ | | | fps | 1109 | | iterations | 250 | | time_elapsed | 1845 | | total_timesteps | 2048000 | | train/ | | | approx_kl | 0.11758677 | | clip_fraction | 0.52 | | clip_range | 0.147 | | entropy_loss | -6.69 | | explained_variance | 0.543 | | learning_rate | 0.000245 | | loss | -0.0815 | | n_updates | 996 | | policy_gradient_loss | -0.052 | | value_loss | 0.000712 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 238 | | ep_rew_mean | 0.332 | | time/ | | | fps | 1109 | | iterations | 251 | | time_elapsed | 1853 | | total_timesteps | 2056192 | | train/ | | | approx_kl | 0.10824573 | | clip_fraction | 0.522 | | clip_range | 0.147 | | entropy_loss | -6.7 | | explained_variance | 0.554 | | learning_rate | 0.000245 | | loss | -0.0836 | | n_updates | 1000 | | policy_gradient_loss | -0.0525 | | value_loss | 0.000679 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 244 | | ep_rew_mean | 0.331 | | time/ | | | fps | 1109 | | iterations | 252 | | time_elapsed | 1860 | | total_timesteps | 2064384 | | train/ | | | approx_kl | 0.11809596 | | clip_fraction | 0.526 | | clip_range | 0.147 | | entropy_loss | -6.71 | | explained_variance | 0.553 | | learning_rate | 0.000245 | | loss | -0.0845 | | n_updates | 1004 | | policy_gradient_loss | -0.0532 | | value_loss | 0.000707 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 239 | | ep_rew_mean | 0.33 | | time/ | | | fps | 1109 | | iterations | 253 | | time_elapsed | 1867 | | total_timesteps | 2072576 | | train/ | | | approx_kl | 0.11030411 | | clip_fraction | 0.517 | | clip_range | 0.147 | | entropy_loss | -6.66 | | explained_variance | 0.58 | | learning_rate | 0.000245 | | loss | -0.0853 | | n_updates | 1008 | | policy_gradient_loss | -0.0527 | | value_loss | 0.000696 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 235 | | ep_rew_mean | 0.363 | | time/ | | | fps | 1110 | | iterations | 254 | | time_elapsed | 1874 | | total_timesteps | 2080768 | | train/ | | | approx_kl | 0.106722206 | | clip_fraction | 0.518 | | clip_range | 0.147 | | entropy_loss | -6.63 | | explained_variance | 0.588 | | learning_rate | 0.000245 | | loss | -0.0868 | | n_updates | 1012 | | policy_gradient_loss | -0.0539 | | value_loss | 0.000647 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 239 | | ep_rew_mean | 0.38 | | time/ | | | fps | 1110 | | iterations | 255 | | time_elapsed | 1881 | | total_timesteps | 2088960 | | train/ | | | approx_kl | 0.10282806 | | clip_fraction | 0.515 | | clip_range | 0.147 | | entropy_loss | -6.59 | | explained_variance | 0.533 | | learning_rate | 0.000245 | | loss | -0.0815 | | n_updates | 1016 | | policy_gradient_loss | -0.0513 | | value_loss | 0.000837 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 243 | | ep_rew_mean | 0.396 | | time/ | | | fps | 1110 | | iterations | 256 | | time_elapsed | 1888 | | total_timesteps | 2097152 | | train/ | | | approx_kl | 0.105213836 | | clip_fraction | 0.523 | | clip_range | 0.147 | | entropy_loss | -6.64 | | explained_variance | 0.553 | | learning_rate | 0.000245 | | loss | -0.082 | | n_updates | 1020 | | policy_gradient_loss | -0.0533 | | value_loss | 0.000672 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 247 | | ep_rew_mean | 0.373 | | time/ | | | fps | 1110 | | iterations | 257 | | time_elapsed | 1895 | | total_timesteps | 2105344 | | train/ | | | approx_kl | 0.12586427 | | clip_fraction | 0.518 | | clip_range | 0.147 | | entropy_loss | -6.64 | | explained_variance | 0.504 | | learning_rate | 0.000245 | | loss | -0.0802 | | n_updates | 1024 | | policy_gradient_loss | -0.0521 | | value_loss | 0.000706 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 245 | | ep_rew_mean | 0.373 | | time/ | | | fps | 1110 | | iterations | 258 | | time_elapsed | 1902 | | total_timesteps | 2113536 | | train/ | | | approx_kl | 0.11450364 | | clip_fraction | 0.525 | | clip_range | 0.147 | | entropy_loss | -6.67 | | explained_variance | 0.55 | | learning_rate | 0.000245 | | loss | -0.0845 | | n_updates | 1028 | | policy_gradient_loss | -0.0524 | | value_loss | 0.000756 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 248 | | ep_rew_mean | 0.365 | | time/ | | | fps | 1110 | | iterations | 259 | | time_elapsed | 1909 | | total_timesteps | 2121728 | | train/ | | | approx_kl | 0.11675545 | | clip_fraction | 0.532 | | clip_range | 0.147 | | entropy_loss | -6.66 | | explained_variance | 0.572 | | learning_rate | 0.000245 | | loss | -0.0817 | | n_updates | 1032 | | policy_gradient_loss | -0.0528 | | value_loss | 0.000662 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 249 | | ep_rew_mean | 0.348 | | time/ | | | fps | 1111 | | iterations | 260 | | time_elapsed | 1917 | | total_timesteps | 2129920 | | train/ | | | approx_kl | 0.11905363 | | clip_fraction | 0.522 | | clip_range | 0.147 | | entropy_loss | -6.7 | | explained_variance | 0.539 | | learning_rate | 0.000245 | | loss | -0.0863 | | n_updates | 1036 | | policy_gradient_loss | -0.0515 | | value_loss | 0.000692 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 245 | | ep_rew_mean | 0.359 | | time/ | | | fps | 1111 | | iterations | 261 | | time_elapsed | 1924 | | total_timesteps | 2138112 | | train/ | | | approx_kl | 0.13341506 | | clip_fraction | 0.537 | | clip_range | 0.147 | | entropy_loss | -6.62 | | explained_variance | 0.575 | | learning_rate | 0.000245 | | loss | -0.0802 | | n_updates | 1040 | | policy_gradient_loss | -0.0534 | | value_loss | 0.000626 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 235 | | ep_rew_mean | 0.359 | | time/ | | | fps | 1111 | | iterations | 262 | | time_elapsed | 1931 | | total_timesteps | 2146304 | | train/ | | | approx_kl | 0.12757908 | | clip_fraction | 0.537 | | clip_range | 0.147 | | entropy_loss | -6.59 | | explained_variance | 0.534 | | learning_rate | 0.000245 | | loss | -0.0836 | | n_updates | 1044 | | policy_gradient_loss | -0.0542 | | value_loss | 0.000829 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 226 | | ep_rew_mean | 0.376 | | time/ | | | fps | 1111 | | iterations | 263 | | time_elapsed | 1938 | | total_timesteps | 2154496 | | train/ | | | approx_kl | 0.11697957 | | clip_fraction | 0.524 | | clip_range | 0.147 | | entropy_loss | -6.6 | | explained_variance | 0.555 | | learning_rate | 0.000245 | | loss | -0.0884 | | n_updates | 1048 | | policy_gradient_loss | -0.0525 | | value_loss | 0.000711 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 231 | | ep_rew_mean | 0.353 | | time/ | | | fps | 1111 | | iterations | 264 | | time_elapsed | 1945 | | total_timesteps | 2162688 | | train/ | | | approx_kl | 0.11898437 | | clip_fraction | 0.523 | | clip_range | 0.147 | | entropy_loss | -6.63 | | explained_variance | 0.544 | | learning_rate | 0.000245 | | loss | -0.0863 | | n_updates | 1052 | | policy_gradient_loss | -0.0543 | | value_loss | 0.000796 | ---------------------------------------- --------------------------------------- | rollout/ | | | ep_len_mean | 230 | | ep_rew_mean | 0.361 | | time/ | | | fps | 1111 | | iterations | 265 | | time_elapsed | 1952 | | total_timesteps | 2170880 | | train/ | | | approx_kl | 0.1116631 | | clip_fraction | 0.52 | | clip_range | 0.147 | | entropy_loss | -6.64 | | explained_variance | 0.528 | | learning_rate | 0.000245 | | loss | -0.0835 | | n_updates | 1056 | | policy_gradient_loss | -0.0524 | | value_loss | 0.000793 | --------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 239 | | ep_rew_mean | 0.347 | | time/ | | | fps | 1112 | | iterations | 266 | | time_elapsed | 1959 | | total_timesteps | 2179072 | | train/ | | | approx_kl | 0.12220342 | | clip_fraction | 0.536 | | clip_range | 0.147 | | entropy_loss | -6.63 | | explained_variance | 0.542 | | learning_rate | 0.000245 | | loss | -0.0847 | | n_updates | 1060 | | policy_gradient_loss | -0.0539 | | value_loss | 0.000742 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 236 | | ep_rew_mean | 0.354 | | time/ | | | fps | 1112 | | iterations | 267 | | time_elapsed | 1966 | | total_timesteps | 2187264 | | train/ | | | approx_kl | 0.11984712 | | clip_fraction | 0.526 | | clip_range | 0.147 | | entropy_loss | -6.65 | | explained_variance | 0.563 | | learning_rate | 0.000245 | | loss | -0.0796 | | n_updates | 1064 | | policy_gradient_loss | -0.0497 | | value_loss | 0.000698 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 229 | | ep_rew_mean | 0.348 | | time/ | | | fps | 1112 | | iterations | 268 | | time_elapsed | 1973 | | total_timesteps | 2195456 | | train/ | | | approx_kl | 0.16792664 | | clip_fraction | 0.522 | | clip_range | 0.147 | | entropy_loss | -6.64 | | explained_variance | 0.543 | | learning_rate | 0.000245 | | loss | -0.0774 | | n_updates | 1068 | | policy_gradient_loss | -0.0528 | | value_loss | 0.000834 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 225 | | ep_rew_mean | 0.355 | | time/ | | | fps | 1112 | | iterations | 269 | | time_elapsed | 1980 | | total_timesteps | 2203648 | | train/ | | | approx_kl | 0.13075173 | | clip_fraction | 0.543 | | clip_range | 0.147 | | entropy_loss | -6.57 | | explained_variance | 0.549 | | learning_rate | 0.000245 | | loss | -0.0802 | | n_updates | 1072 | | policy_gradient_loss | -0.0535 | | value_loss | 0.000738 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 232 | | ep_rew_mean | 0.349 | | time/ | | | fps | 1112 | | iterations | 270 | | time_elapsed | 1987 | | total_timesteps | 2211840 | | train/ | | | approx_kl | 0.13127384 | | clip_fraction | 0.549 | | clip_range | 0.147 | | entropy_loss | -6.56 | | explained_variance | 0.528 | | learning_rate | 0.000245 | | loss | -0.0763 | | n_updates | 1076 | | policy_gradient_loss | -0.052 | | value_loss | 0.000766 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 238 | | ep_rew_mean | 0.366 | | time/ | | | fps | 1112 | | iterations | 271 | | time_elapsed | 1994 | | total_timesteps | 2220032 | | train/ | | | approx_kl | 0.118666574 | | clip_fraction | 0.538 | | clip_range | 0.147 | | entropy_loss | -6.6 | | explained_variance | 0.56 | | learning_rate | 0.000245 | | loss | -0.0835 | | n_updates | 1080 | | policy_gradient_loss | -0.0531 | | value_loss | 0.000697 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 233 | | ep_rew_mean | 0.37 | | time/ | | | fps | 1112 | | iterations | 272 | | time_elapsed | 2002 | | total_timesteps | 2228224 | | train/ | | | approx_kl | 0.12737373 | | clip_fraction | 0.548 | | clip_range | 0.147 | | entropy_loss | -6.5 | | explained_variance | 0.578 | | learning_rate | 0.000245 | | loss | -0.0857 | | n_updates | 1084 | | policy_gradient_loss | -0.0556 | | value_loss | 0.000714 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 231 | | ep_rew_mean | 0.401 | | time/ | | | fps | 1112 | | iterations | 273 | | time_elapsed | 2009 | | total_timesteps | 2236416 | | train/ | | | approx_kl | 0.13086809 | | clip_fraction | 0.543 | | clip_range | 0.147 | | entropy_loss | -6.54 | | explained_variance | 0.54 | | learning_rate | 0.000244 | | loss | -0.0868 | | n_updates | 1088 | | policy_gradient_loss | -0.0541 | | value_loss | 0.000744 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 225 | | ep_rew_mean | 0.404 | | time/ | | | fps | 1113 | | iterations | 274 | | time_elapsed | 2016 | | total_timesteps | 2244608 | | train/ | | | approx_kl | 0.13590792 | | clip_fraction | 0.531 | | clip_range | 0.147 | | entropy_loss | -6.45 | | explained_variance | 0.517 | | learning_rate | 0.000244 | | loss | -0.0864 | | n_updates | 1092 | | policy_gradient_loss | -0.0538 | | value_loss | 0.000909 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 227 | | ep_rew_mean | 0.404 | | time/ | | | fps | 1113 | | iterations | 275 | | time_elapsed | 2023 | | total_timesteps | 2252800 | | train/ | | | approx_kl | 0.119182885 | | clip_fraction | 0.537 | | clip_range | 0.147 | | entropy_loss | -6.41 | | explained_variance | 0.548 | | learning_rate | 0.000244 | | loss | -0.0758 | | n_updates | 1096 | | policy_gradient_loss | -0.053 | | value_loss | 0.000867 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 227 | | ep_rew_mean | 0.394 | | time/ | | | fps | 1113 | | iterations | 276 | | time_elapsed | 2030 | | total_timesteps | 2260992 | | train/ | | | approx_kl | 0.14524022 | | clip_fraction | 0.549 | | clip_range | 0.147 | | entropy_loss | -6.52 | | explained_variance | 0.56 | | learning_rate | 0.000244 | | loss | -0.0886 | | n_updates | 1100 | | policy_gradient_loss | -0.0541 | | value_loss | 0.00072 | ---------------------------------------- -------------------------------------- | rollout/ | | | ep_len_mean | 225 | | ep_rew_mean | 0.384 | | time/ | | | fps | 1113 | | iterations | 277 | | time_elapsed | 2037 | | total_timesteps | 2269184 | | train/ | | | approx_kl | 0.129794 | | clip_fraction | 0.546 | | clip_range | 0.147 | | entropy_loss | -6.41 | | explained_variance | 0.522 | | learning_rate | 0.000244 | | loss | -0.0844 | | n_updates | 1104 | | policy_gradient_loss | -0.0513 | | value_loss | 0.000923 | -------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 223 | | ep_rew_mean | 0.395 | | time/ | | | fps | 1113 | | iterations | 278 | | time_elapsed | 2045 | | total_timesteps | 2277376 | | train/ | | | approx_kl | 0.13621642 | | clip_fraction | 0.556 | | clip_range | 0.147 | | entropy_loss | -6.42 | | explained_variance | 0.527 | | learning_rate | 0.000244 | | loss | -0.0912 | | n_updates | 1108 | | policy_gradient_loss | -0.0559 | | value_loss | 0.000799 | ---------------------------------------- --------------------------------------- | rollout/ | | | ep_len_mean | 227 | | ep_rew_mean | 0.376 | | time/ | | | fps | 1113 | | iterations | 279 | | time_elapsed | 2052 | | total_timesteps | 2285568 | | train/ | | | approx_kl | 0.1455627 | | clip_fraction | 0.55 | | clip_range | 0.147 | | entropy_loss | -6.44 | | explained_variance | 0.579 | | learning_rate | 0.000244 | | loss | -0.0862 | | n_updates | 1112 | | policy_gradient_loss | -0.055 | | value_loss | 0.000726 | --------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 230 | | ep_rew_mean | 0.356 | | time/ | | | fps | 1113 | | iterations | 280 | | time_elapsed | 2059 | | total_timesteps | 2293760 | | train/ | | | approx_kl | 0.13505621 | | clip_fraction | 0.54 | | clip_range | 0.147 | | entropy_loss | -6.39 | | explained_variance | 0.547 | | learning_rate | 0.000244 | | loss | -0.082 | | n_updates | 1116 | | policy_gradient_loss | -0.0514 | | value_loss | 0.000834 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 231 | | ep_rew_mean | 0.362 | | time/ | | | fps | 1113 | | iterations | 281 | | time_elapsed | 2066 | | total_timesteps | 2301952 | | train/ | | | approx_kl | 0.14478296 | | clip_fraction | 0.543 | | clip_range | 0.147 | | entropy_loss | -6.49 | | explained_variance | 0.567 | | learning_rate | 0.000244 | | loss | -0.0916 | | n_updates | 1120 | | policy_gradient_loss | -0.0537 | | value_loss | 0.000716 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 233 | | ep_rew_mean | 0.379 | | time/ | | | fps | 1114 | | iterations | 282 | | time_elapsed | 2073 | | total_timesteps | 2310144 | | train/ | | | approx_kl | 0.16083223 | | clip_fraction | 0.551 | | clip_range | 0.147 | | entropy_loss | -6.44 | | explained_variance | 0.557 | | learning_rate | 0.000244 | | loss | -0.0827 | | n_updates | 1124 | | policy_gradient_loss | -0.0546 | | value_loss | 0.000744 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 225 | | ep_rew_mean | 0.428 | | time/ | | | fps | 1114 | | iterations | 283 | | time_elapsed | 2080 | | total_timesteps | 2318336 | | train/ | | | approx_kl | 0.13430959 | | clip_fraction | 0.53 | | clip_range | 0.147 | | entropy_loss | -6.42 | | explained_variance | 0.543 | | learning_rate | 0.000244 | | loss | -0.0831 | | n_updates | 1128 | | policy_gradient_loss | -0.0523 | | value_loss | 0.00089 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 226 | | ep_rew_mean | 0.411 | | time/ | | | fps | 1114 | | iterations | 284 | | time_elapsed | 2087 | | total_timesteps | 2326528 | | train/ | | | approx_kl | 0.12128008 | | clip_fraction | 0.536 | | clip_range | 0.147 | | entropy_loss | -6.42 | | explained_variance | 0.497 | | learning_rate | 0.000244 | | loss | -0.0831 | | n_updates | 1132 | | policy_gradient_loss | -0.0543 | | value_loss | 0.000951 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 228 | | ep_rew_mean | 0.427 | | time/ | | | fps | 1114 | | iterations | 285 | | time_elapsed | 2094 | | total_timesteps | 2334720 | | train/ | | | approx_kl | 0.13199475 | | clip_fraction | 0.55 | | clip_range | 0.147 | | entropy_loss | -6.39 | | explained_variance | 0.55 | | learning_rate | 0.000244 | | loss | -0.0874 | | n_updates | 1136 | | policy_gradient_loss | -0.0549 | | value_loss | 0.000778 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 231 | | ep_rew_mean | 0.421 | | time/ | | | fps | 1114 | | iterations | 286 | | time_elapsed | 2101 | | total_timesteps | 2342912 | | train/ | | | approx_kl | 0.17001414 | | clip_fraction | 0.542 | | clip_range | 0.147 | | entropy_loss | -6.44 | | explained_variance | 0.504 | | learning_rate | 0.000244 | | loss | -0.0849 | | n_updates | 1140 | | policy_gradient_loss | -0.0529 | | value_loss | 0.000868 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 229 | | ep_rew_mean | 0.447 | | time/ | | | fps | 1114 | | iterations | 287 | | time_elapsed | 2109 | | total_timesteps | 2351104 | | train/ | | | approx_kl | 0.12955865 | | clip_fraction | 0.546 | | clip_range | 0.147 | | entropy_loss | -6.29 | | explained_variance | 0.57 | | learning_rate | 0.000244 | | loss | -0.0821 | | n_updates | 1144 | | policy_gradient_loss | -0.0537 | | value_loss | 0.000795 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 225 | | ep_rew_mean | 0.424 | | time/ | | | fps | 1114 | | iterations | 288 | | time_elapsed | 2116 | | total_timesteps | 2359296 | | train/ | | | approx_kl | 0.14553112 | | clip_fraction | 0.55 | | clip_range | 0.147 | | entropy_loss | -6.38 | | explained_variance | 0.537 | | learning_rate | 0.000244 | | loss | -0.0831 | | n_updates | 1148 | | policy_gradient_loss | -0.0534 | | value_loss | 0.000844 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 228 | | ep_rew_mean | 0.411 | | time/ | | | fps | 1115 | | iterations | 289 | | time_elapsed | 2123 | | total_timesteps | 2367488 | | train/ | | | approx_kl | 0.13292184 | | clip_fraction | 0.546 | | clip_range | 0.147 | | entropy_loss | -6.3 | | explained_variance | 0.528 | | learning_rate | 0.000244 | | loss | -0.0843 | | n_updates | 1152 | | policy_gradient_loss | -0.0516 | | value_loss | 0.000929 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 224 | | ep_rew_mean | 0.4 | | time/ | | | fps | 1115 | | iterations | 290 | | time_elapsed | 2130 | | total_timesteps | 2375680 | | train/ | | | approx_kl | 0.13757321 | | clip_fraction | 0.546 | | clip_range | 0.147 | | entropy_loss | -6.28 | | explained_variance | 0.558 | | learning_rate | 0.000244 | | loss | -0.0844 | | n_updates | 1156 | | policy_gradient_loss | -0.0545 | | value_loss | 0.000779 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 224 | | ep_rew_mean | 0.425 | | time/ | | | fps | 1115 | | iterations | 291 | | time_elapsed | 2137 | | total_timesteps | 2383872 | | train/ | | | approx_kl | 0.13122205 | | clip_fraction | 0.545 | | clip_range | 0.147 | | entropy_loss | -6.33 | | explained_variance | 0.541 | | learning_rate | 0.000244 | | loss | -0.0822 | | n_updates | 1160 | | policy_gradient_loss | -0.0535 | | value_loss | 0.00085 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 224 | | ep_rew_mean | 0.438 | | time/ | | | fps | 1115 | | iterations | 292 | | time_elapsed | 2144 | | total_timesteps | 2392064 | | train/ | | | approx_kl | 0.12804487 | | clip_fraction | 0.528 | | clip_range | 0.147 | | entropy_loss | -6.23 | | explained_variance | 0.544 | | learning_rate | 0.000244 | | loss | -0.0797 | | n_updates | 1164 | | policy_gradient_loss | -0.0499 | | value_loss | 0.00102 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 223 | | ep_rew_mean | 0.423 | | time/ | | | fps | 1115 | | iterations | 293 | | time_elapsed | 2152 | | total_timesteps | 2400256 | | train/ | | | approx_kl | 0.121570036 | | clip_fraction | 0.538 | | clip_range | 0.147 | | entropy_loss | -6.24 | | explained_variance | 0.54 | | learning_rate | 0.000244 | | loss | -0.085 | | n_updates | 1168 | | policy_gradient_loss | -0.054 | | value_loss | 0.000885 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 224 | | ep_rew_mean | 0.457 | | time/ | | | fps | 1115 | | iterations | 294 | | time_elapsed | 2159 | | total_timesteps | 2408448 | | train/ | | | approx_kl | 0.12496737 | | clip_fraction | 0.532 | | clip_range | 0.147 | | entropy_loss | -6.24 | | explained_variance | 0.568 | | learning_rate | 0.000244 | | loss | -0.0825 | | n_updates | 1172 | | policy_gradient_loss | -0.0523 | | value_loss | 0.00091 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 214 | | ep_rew_mean | 0.485 | | time/ | | | fps | 1115 | | iterations | 295 | | time_elapsed | 2166 | | total_timesteps | 2416640 | | train/ | | | approx_kl | 0.14364733 | | clip_fraction | 0.549 | | clip_range | 0.147 | | entropy_loss | -6.2 | | explained_variance | 0.544 | | learning_rate | 0.000244 | | loss | -0.0859 | | n_updates | 1176 | | policy_gradient_loss | -0.0539 | | value_loss | 0.000999 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 213 | | ep_rew_mean | 0.48 | | time/ | | | fps | 1115 | | iterations | 296 | | time_elapsed | 2173 | | total_timesteps | 2424832 | | train/ | | | approx_kl | 0.11831698 | | clip_fraction | 0.543 | | clip_range | 0.147 | | entropy_loss | -6.12 | | explained_variance | 0.553 | | learning_rate | 0.000244 | | loss | -0.0866 | | n_updates | 1180 | | policy_gradient_loss | -0.0527 | | value_loss | 0.00106 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 206 | | ep_rew_mean | 0.478 | | time/ | | | fps | 1115 | | iterations | 297 | | time_elapsed | 2180 | | total_timesteps | 2433024 | | train/ | | | approx_kl | 0.14491293 | | clip_fraction | 0.543 | | clip_range | 0.147 | | entropy_loss | -6.18 | | explained_variance | 0.578 | | learning_rate | 0.000244 | | loss | -0.084 | | n_updates | 1184 | | policy_gradient_loss | -0.053 | | value_loss | 0.000972 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 208 | | ep_rew_mean | 0.465 | | time/ | | | fps | 1115 | | iterations | 298 | | time_elapsed | 2188 | | total_timesteps | 2441216 | | train/ | | | approx_kl | 0.13459009 | | clip_fraction | 0.554 | | clip_range | 0.147 | | entropy_loss | -6.1 | | explained_variance | 0.505 | | learning_rate | 0.000244 | | loss | -0.0811 | | n_updates | 1188 | | policy_gradient_loss | -0.0506 | | value_loss | 0.00119 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 204 | | ep_rew_mean | 0.453 | | time/ | | | fps | 1115 | | iterations | 299 | | time_elapsed | 2195 | | total_timesteps | 2449408 | | train/ | | | approx_kl | 0.13332029 | | clip_fraction | 0.555 | | clip_range | 0.147 | | entropy_loss | -6.13 | | explained_variance | 0.578 | | learning_rate | 0.000244 | | loss | -0.0761 | | n_updates | 1192 | | policy_gradient_loss | -0.0518 | | value_loss | 0.000869 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 201 | | ep_rew_mean | 0.481 | | time/ | | | fps | 1115 | | iterations | 300 | | time_elapsed | 2202 | | total_timesteps | 2457600 | | train/ | | | approx_kl | 0.12881124 | | clip_fraction | 0.549 | | clip_range | 0.147 | | entropy_loss | -6.12 | | explained_variance | 0.611 | | learning_rate | 0.000244 | | loss | -0.074 | | n_updates | 1196 | | policy_gradient_loss | -0.048 | | value_loss | 0.000997 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 200 | | ep_rew_mean | 0.501 | | time/ | | | fps | 1115 | | iterations | 301 | | time_elapsed | 2210 | | total_timesteps | 2465792 | | train/ | | | approx_kl | 0.13601755 | | clip_fraction | 0.548 | | clip_range | 0.147 | | entropy_loss | -6.04 | | explained_variance | 0.548 | | learning_rate | 0.000244 | | loss | -0.0755 | | n_updates | 1200 | | policy_gradient_loss | -0.0498 | | value_loss | 0.00125 | ---------------------------------------- --------------------------------------- | rollout/ | | | ep_len_mean | 204 | | ep_rew_mean | 0.494 | | time/ | | | fps | 1115 | | iterations | 302 | | time_elapsed | 2217 | | total_timesteps | 2473984 | | train/ | | | approx_kl | 0.1639984 | | clip_fraction | 0.541 | | clip_range | 0.147 | | entropy_loss | -6.06 | | explained_variance | 0.556 | | learning_rate | 0.000244 | | loss | -0.0799 | | n_updates | 1204 | | policy_gradient_loss | -0.0491 | | value_loss | 0.00111 | --------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 211 | | ep_rew_mean | 0.473 | | time/ | | | fps | 1115 | | iterations | 303 | | time_elapsed | 2224 | | total_timesteps | 2482176 | | train/ | | | approx_kl | 0.15511459 | | clip_fraction | 0.545 | | clip_range | 0.147 | | entropy_loss | -6.06 | | explained_variance | 0.58 | | learning_rate | 0.000244 | | loss | -0.0837 | | n_updates | 1208 | | policy_gradient_loss | -0.052 | | value_loss | 0.00105 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 193 | | ep_rew_mean | 0.519 | | time/ | | | fps | 1115 | | iterations | 304 | | time_elapsed | 2232 | | total_timesteps | 2490368 | | train/ | | | approx_kl | 0.13812377 | | clip_fraction | 0.55 | | clip_range | 0.147 | | entropy_loss | -6.07 | | explained_variance | 0.572 | | learning_rate | 0.000244 | | loss | -0.0802 | | n_updates | 1212 | | policy_gradient_loss | -0.0509 | | value_loss | 0.000973 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 182 | | ep_rew_mean | 0.547 | | time/ | | | fps | 1115 | | iterations | 305 | | time_elapsed | 2239 | | total_timesteps | 2498560 | | train/ | | | approx_kl | 0.14407986 | | clip_fraction | 0.543 | | clip_range | 0.147 | | entropy_loss | -5.82 | | explained_variance | 0.548 | | learning_rate | 0.000244 | | loss | -0.0762 | | n_updates | 1216 | | policy_gradient_loss | -0.0489 | | value_loss | 0.00158 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 195 | | ep_rew_mean | 0.517 | | time/ | | | fps | 1115 | | iterations | 306 | | time_elapsed | 2246 | | total_timesteps | 2506752 | | train/ | | | approx_kl | 0.15691206 | | clip_fraction | 0.54 | | clip_range | 0.147 | | entropy_loss | -5.99 | | explained_variance | 0.549 | | learning_rate | 0.000244 | | loss | -0.0731 | | n_updates | 1220 | | policy_gradient_loss | -0.0498 | | value_loss | 0.00137 | ---------------------------------------- -------------------------------------- | rollout/ | | | ep_len_mean | 204 | | ep_rew_mean | 0.472 | | time/ | | | fps | 1116 | | iterations | 307 | | time_elapsed | 2253 | | total_timesteps | 2514944 | | train/ | | | approx_kl | 0.132661 | | clip_fraction | 0.545 | | clip_range | 0.147 | | entropy_loss | -6.07 | | explained_variance | 0.604 | | learning_rate | 0.000244 | | loss | -0.0873 | | n_updates | 1224 | | policy_gradient_loss | -0.0528 | | value_loss | 0.00101 | -------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 209 | | ep_rew_mean | 0.465 | | time/ | | | fps | 1116 | | iterations | 308 | | time_elapsed | 2260 | | total_timesteps | 2523136 | | train/ | | | approx_kl | 0.12463517 | | clip_fraction | 0.538 | | clip_range | 0.147 | | entropy_loss | -6.06 | | explained_variance | 0.642 | | learning_rate | 0.000244 | | loss | -0.0617 | | n_updates | 1228 | | policy_gradient_loss | -0.0489 | | value_loss | 0.000952 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 201 | | ep_rew_mean | 0.493 | | time/ | | | fps | 1116 | | iterations | 309 | | time_elapsed | 2267 | | total_timesteps | 2531328 | | train/ | | | approx_kl | 0.15407297 | | clip_fraction | 0.534 | | clip_range | 0.147 | | entropy_loss | -6.08 | | explained_variance | 0.645 | | learning_rate | 0.000244 | | loss | -0.0748 | | n_updates | 1232 | | policy_gradient_loss | -0.0512 | | value_loss | 0.00103 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 190 | | ep_rew_mean | 0.514 | | time/ | | | fps | 1116 | | iterations | 310 | | time_elapsed | 2274 | | total_timesteps | 2539520 | | train/ | | | approx_kl | 0.12622729 | | clip_fraction | 0.531 | | clip_range | 0.147 | | entropy_loss | -6.06 | | explained_variance | 0.642 | | learning_rate | 0.000244 | | loss | -0.078 | | n_updates | 1236 | | policy_gradient_loss | -0.0512 | | value_loss | 0.0011 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 190 | | ep_rew_mean | 0.524 | | time/ | | | fps | 1116 | | iterations | 311 | | time_elapsed | 2281 | | total_timesteps | 2547712 | | train/ | | | approx_kl | 0.15339619 | | clip_fraction | 0.542 | | clip_range | 0.147 | | entropy_loss | -6.04 | | explained_variance | 0.629 | | learning_rate | 0.000244 | | loss | -0.0824 | | n_updates | 1240 | | policy_gradient_loss | -0.0505 | | value_loss | 0.0011 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 177 | | ep_rew_mean | 0.566 | | time/ | | | fps | 1116 | | iterations | 312 | | time_elapsed | 2288 | | total_timesteps | 2555904 | | train/ | | | approx_kl | 0.12907922 | | clip_fraction | 0.538 | | clip_range | 0.147 | | entropy_loss | -5.95 | | explained_variance | 0.6 | | learning_rate | 0.000244 | | loss | -0.0687 | | n_updates | 1244 | | policy_gradient_loss | -0.0453 | | value_loss | 0.00137 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 177 | | ep_rew_mean | 0.586 | | time/ | | | fps | 1116 | | iterations | 313 | | time_elapsed | 2295 | | total_timesteps | 2564096 | | train/ | | | approx_kl | 0.13883483 | | clip_fraction | 0.518 | | clip_range | 0.147 | | entropy_loss | -6.01 | | explained_variance | 0.568 | | learning_rate | 0.000244 | | loss | -0.0734 | | n_updates | 1248 | | policy_gradient_loss | -0.0475 | | value_loss | 0.00157 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 183 | | ep_rew_mean | 0.565 | | time/ | | | fps | 1116 | | iterations | 314 | | time_elapsed | 2303 | | total_timesteps | 2572288 | | train/ | | | approx_kl | 0.14125925 | | clip_fraction | 0.521 | | clip_range | 0.147 | | entropy_loss | -6.04 | | explained_variance | 0.591 | | learning_rate | 0.000244 | | loss | -0.0724 | | n_updates | 1252 | | policy_gradient_loss | -0.0472 | | value_loss | 0.00157 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 185 | | ep_rew_mean | 0.555 | | time/ | | | fps | 1116 | | iterations | 315 | | time_elapsed | 2310 | | total_timesteps | 2580480 | | train/ | | | approx_kl | 0.13967541 | | clip_fraction | 0.53 | | clip_range | 0.147 | | entropy_loss | -6.05 | | explained_variance | 0.599 | | learning_rate | 0.000244 | | loss | -0.0767 | | n_updates | 1256 | | policy_gradient_loss | -0.0512 | | value_loss | 0.00129 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 194 | | ep_rew_mean | 0.527 | | time/ | | | fps | 1116 | | iterations | 316 | | time_elapsed | 2317 | | total_timesteps | 2588672 | | train/ | | | approx_kl | 0.13846168 | | clip_fraction | 0.537 | | clip_range | 0.147 | | entropy_loss | -6.08 | | explained_variance | 0.598 | | learning_rate | 0.000244 | | loss | -0.0798 | | n_updates | 1260 | | policy_gradient_loss | -0.0493 | | value_loss | 0.0012 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 187 | | ep_rew_mean | 0.541 | | time/ | | | fps | 1117 | | iterations | 317 | | time_elapsed | 2324 | | total_timesteps | 2596864 | | train/ | | | approx_kl | 0.15013278 | | clip_fraction | 0.544 | | clip_range | 0.147 | | entropy_loss | -5.97 | | explained_variance | 0.611 | | learning_rate | 0.000244 | | loss | -0.0754 | | n_updates | 1264 | | policy_gradient_loss | -0.0465 | | value_loss | 0.00123 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 169 | | ep_rew_mean | 0.595 | | time/ | | | fps | 1117 | | iterations | 318 | | time_elapsed | 2331 | | total_timesteps | 2605056 | | train/ | | | approx_kl | 0.12882127 | | clip_fraction | 0.539 | | clip_range | 0.147 | | entropy_loss | -5.98 | | explained_variance | 0.606 | | learning_rate | 0.000244 | | loss | -0.069 | | n_updates | 1268 | | policy_gradient_loss | -0.0462 | | value_loss | 0.00148 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 156 | | ep_rew_mean | 0.616 | | time/ | | | fps | 1117 | | iterations | 319 | | time_elapsed | 2338 | | total_timesteps | 2613248 | | train/ | | | approx_kl | 0.14171463 | | clip_fraction | 0.527 | | clip_range | 0.147 | | entropy_loss | -5.91 | | explained_variance | 0.582 | | learning_rate | 0.000244 | | loss | -0.0795 | | n_updates | 1272 | | policy_gradient_loss | -0.0471 | | value_loss | 0.00171 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 150 | | ep_rew_mean | 0.618 | | time/ | | | fps | 1117 | | iterations | 320 | | time_elapsed | 2345 | | total_timesteps | 2621440 | | train/ | | | approx_kl | 0.11437479 | | clip_fraction | 0.538 | | clip_range | 0.147 | | entropy_loss | -5.9 | | explained_variance | 0.595 | | learning_rate | 0.000244 | | loss | -0.0667 | | n_updates | 1276 | | policy_gradient_loss | -0.0441 | | value_loss | 0.00173 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 151 | | ep_rew_mean | 0.631 | | time/ | | | fps | 1117 | | iterations | 321 | | time_elapsed | 2353 | | total_timesteps | 2629632 | | train/ | | | approx_kl | 0.13215554 | | clip_fraction | 0.54 | | clip_range | 0.147 | | entropy_loss | -5.9 | | explained_variance | 0.552 | | learning_rate | 0.000244 | | loss | -0.0677 | | n_updates | 1280 | | policy_gradient_loss | -0.045 | | value_loss | 0.00213 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 137 | | ep_rew_mean | 0.653 | | time/ | | | fps | 1117 | | iterations | 322 | | time_elapsed | 2360 | | total_timesteps | 2637824 | | train/ | | | approx_kl | 0.10379107 | | clip_fraction | 0.523 | | clip_range | 0.147 | | entropy_loss | -5.84 | | explained_variance | 0.646 | | learning_rate | 0.000243 | | loss | -0.0531 | | n_updates | 1284 | | policy_gradient_loss | -0.0399 | | value_loss | 0.00189 | ---------------------------------------- --------------------------------------- | rollout/ | | | ep_len_mean | 126 | | ep_rew_mean | 0.688 | | time/ | | | fps | 1117 | | iterations | 323 | | time_elapsed | 2367 | | total_timesteps | 2646016 | | train/ | | | approx_kl | 0.1383547 | | clip_fraction | 0.527 | | clip_range | 0.147 | | entropy_loss | -5.73 | | explained_variance | 0.623 | | learning_rate | 0.000243 | | loss | -0.0453 | | n_updates | 1288 | | policy_gradient_loss | -0.0356 | | value_loss | 0.00245 | --------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 118 | | ep_rew_mean | 0.699 | | time/ | | | fps | 1117 | | iterations | 324 | | time_elapsed | 2375 | | total_timesteps | 2654208 | | train/ | | | approx_kl | 0.10181295 | | clip_fraction | 0.523 | | clip_range | 0.147 | | entropy_loss | -5.66 | | explained_variance | 0.574 | | learning_rate | 0.000243 | | loss | -0.0586 | | n_updates | 1292 | | policy_gradient_loss | -0.0383 | | value_loss | 0.00286 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 109 | | ep_rew_mean | 0.715 | | time/ | | | fps | 1117 | | iterations | 325 | | time_elapsed | 2382 | | total_timesteps | 2662400 | | train/ | | | approx_kl | 0.10532946 | | clip_fraction | 0.509 | | clip_range | 0.147 | | entropy_loss | -5.69 | | explained_variance | 0.692 | | learning_rate | 0.000243 | | loss | -0.0506 | | n_updates | 1296 | | policy_gradient_loss | -0.0378 | | value_loss | 0.00236 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 100 | | ep_rew_mean | 0.739 | | time/ | | | fps | 1117 | | iterations | 326 | | time_elapsed | 2389 | | total_timesteps | 2670592 | | train/ | | | approx_kl | 0.098842666 | | clip_fraction | 0.492 | | clip_range | 0.147 | | entropy_loss | -5.52 | | explained_variance | 0.747 | | learning_rate | 0.000243 | | loss | -0.0455 | | n_updates | 1300 | | policy_gradient_loss | -0.0305 | | value_loss | 0.00256 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 104 | | ep_rew_mean | 0.724 | | time/ | | | fps | 1117 | | iterations | 327 | | time_elapsed | 2397 | | total_timesteps | 2678784 | | train/ | | | approx_kl | 0.10003296 | | clip_fraction | 0.491 | | clip_range | 0.147 | | entropy_loss | -5.44 | | explained_variance | 0.734 | | learning_rate | 0.000243 | | loss | -0.0553 | | n_updates | 1304 | | policy_gradient_loss | -0.0315 | | value_loss | 0.00293 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 83 | | ep_rew_mean | 0.772 | | time/ | | | fps | 1117 | | iterations | 328 | | time_elapsed | 2404 | | total_timesteps | 2686976 | | train/ | | | approx_kl | 0.088681825 | | clip_fraction | 0.493 | | clip_range | 0.147 | | entropy_loss | -5.4 | | explained_variance | 0.778 | | learning_rate | 0.000243 | | loss | -0.0434 | | n_updates | 1308 | | policy_gradient_loss | -0.0337 | | value_loss | 0.00244 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 75.8 | | ep_rew_mean | 0.791 | | time/ | | | fps | 1117 | | iterations | 329 | | time_elapsed | 2412 | | total_timesteps | 2695168 | | train/ | | | approx_kl | 0.08816405 | | clip_fraction | 0.453 | | clip_range | 0.147 | | entropy_loss | -5.04 | | explained_variance | 0.839 | | learning_rate | 0.000243 | | loss | -0.0451 | | n_updates | 1312 | | policy_gradient_loss | -0.0281 | | value_loss | 0.00208 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 77.8 | | ep_rew_mean | 0.785 | | time/ | | | fps | 1117 | | iterations | 330 | | time_elapsed | 2419 | | total_timesteps | 2703360 | | train/ | | | approx_kl | 0.12182632 | | clip_fraction | 0.477 | | clip_range | 0.147 | | entropy_loss | -4.78 | | explained_variance | 0.865 | | learning_rate | 0.000243 | | loss | -0.0432 | | n_updates | 1316 | | policy_gradient_loss | -0.0287 | | value_loss | 0.00185 | ---------------------------------------- --------------------------------------- | rollout/ | | | ep_len_mean | 75.7 | | ep_rew_mean | 0.78 | | time/ | | | fps | 1117 | | iterations | 331 | | time_elapsed | 2426 | | total_timesteps | 2711552 | | train/ | | | approx_kl | 0.0959728 | | clip_fraction | 0.456 | | clip_range | 0.147 | | entropy_loss | -5.03 | | explained_variance | 0.847 | | learning_rate | 0.000243 | | loss | -0.0328 | | n_updates | 1320 | | policy_gradient_loss | -0.0275 | | value_loss | 0.00218 | --------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 77.2 | | ep_rew_mean | 0.787 | | time/ | | | fps | 1117 | | iterations | 332 | | time_elapsed | 2434 | | total_timesteps | 2719744 | | train/ | | | approx_kl | 0.10346219 | | clip_fraction | 0.442 | | clip_range | 0.147 | | entropy_loss | -4.9 | | explained_variance | 0.832 | | learning_rate | 0.000243 | | loss | -0.0366 | | n_updates | 1324 | | policy_gradient_loss | -0.0284 | | value_loss | 0.00238 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 64.3 | | ep_rew_mean | 0.814 | | time/ | | | fps | 1117 | | iterations | 333 | | time_elapsed | 2441 | | total_timesteps | 2727936 | | train/ | | | approx_kl | 0.10698733 | | clip_fraction | 0.441 | | clip_range | 0.147 | | entropy_loss | -4.84 | | explained_variance | 0.845 | | learning_rate | 0.000243 | | loss | -0.0349 | | n_updates | 1328 | | policy_gradient_loss | -0.0262 | | value_loss | 0.00222 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 66.3 | | ep_rew_mean | 0.812 | | time/ | | | fps | 1117 | | iterations | 334 | | time_elapsed | 2448 | | total_timesteps | 2736128 | | train/ | | | approx_kl | 0.10190974 | | clip_fraction | 0.428 | | clip_range | 0.147 | | entropy_loss | -4.51 | | explained_variance | 0.86 | | learning_rate | 0.000243 | | loss | -0.0352 | | n_updates | 1332 | | policy_gradient_loss | -0.0259 | | value_loss | 0.00195 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 73 | | ep_rew_mean | 0.793 | | time/ | | | fps | 1117 | | iterations | 335 | | time_elapsed | 2456 | | total_timesteps | 2744320 | | train/ | | | approx_kl | 0.12077798 | | clip_fraction | 0.442 | | clip_range | 0.147 | | entropy_loss | -4.67 | | explained_variance | 0.893 | | learning_rate | 0.000243 | | loss | -0.039 | | n_updates | 1336 | | policy_gradient_loss | -0.0255 | | value_loss | 0.00159 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 57.8 | | ep_rew_mean | 0.827 | | time/ | | | fps | 1117 | | iterations | 336 | | time_elapsed | 2463 | | total_timesteps | 2752512 | | train/ | | | approx_kl | 0.11206142 | | clip_fraction | 0.474 | | clip_range | 0.147 | | entropy_loss | -4.72 | | explained_variance | 0.859 | | learning_rate | 0.000243 | | loss | -0.0371 | | n_updates | 1340 | | policy_gradient_loss | -0.0279 | | value_loss | 0.00209 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 69 | | ep_rew_mean | 0.804 | | time/ | | | fps | 1117 | | iterations | 337 | | time_elapsed | 2471 | | total_timesteps | 2760704 | | train/ | | | approx_kl | 0.121503904 | | clip_fraction | 0.416 | | clip_range | 0.147 | | entropy_loss | -4.27 | | explained_variance | 0.867 | | learning_rate | 0.000243 | | loss | -0.0233 | | n_updates | 1344 | | policy_gradient_loss | -0.0209 | | value_loss | 0.00172 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 75.4 | | ep_rew_mean | 0.79 | | time/ | | | fps | 1117 | | iterations | 338 | | time_elapsed | 2478 | | total_timesteps | 2768896 | | train/ | | | approx_kl | 0.090770155 | | clip_fraction | 0.44 | | clip_range | 0.147 | | entropy_loss | -4.68 | | explained_variance | 0.885 | | learning_rate | 0.000243 | | loss | -0.0503 | | n_updates | 1348 | | policy_gradient_loss | -0.0325 | | value_loss | 0.00158 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 59.7 | | ep_rew_mean | 0.826 | | time/ | | | fps | 1117 | | iterations | 339 | | time_elapsed | 2486 | | total_timesteps | 2777088 | | train/ | | | approx_kl | 0.09936334 | | clip_fraction | 0.473 | | clip_range | 0.147 | | entropy_loss | -4.83 | | explained_variance | 0.868 | | learning_rate | 0.000243 | | loss | -0.0476 | | n_updates | 1352 | | policy_gradient_loss | -0.034 | | value_loss | 0.0019 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 57.3 | | ep_rew_mean | 0.831 | | time/ | | | fps | 1117 | | iterations | 340 | | time_elapsed | 2493 | | total_timesteps | 2785280 | | train/ | | | approx_kl | 0.09695612 | | clip_fraction | 0.444 | | clip_range | 0.147 | | entropy_loss | -4.37 | | explained_variance | 0.894 | | learning_rate | 0.000243 | | loss | -0.0267 | | n_updates | 1356 | | policy_gradient_loss | -0.0245 | | value_loss | 0.00148 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 69 | | ep_rew_mean | 0.803 | | time/ | | | fps | 1116 | | iterations | 341 | | time_elapsed | 2500 | | total_timesteps | 2793472 | | train/ | | | approx_kl | 0.10034038 | | clip_fraction | 0.423 | | clip_range | 0.147 | | entropy_loss | -4.35 | | explained_variance | 0.876 | | learning_rate | 0.000243 | | loss | -0.0401 | | n_updates | 1360 | | policy_gradient_loss | -0.0258 | | value_loss | 0.00157 | ---------------------------------------- --------------------------------------- | rollout/ | | | ep_len_mean | 68 | | ep_rew_mean | 0.8 | | time/ | | | fps | 1116 | | iterations | 342 | | time_elapsed | 2508 | | total_timesteps | 2801664 | | train/ | | | approx_kl | 0.0823106 | | clip_fraction | 0.432 | | clip_range | 0.147 | | entropy_loss | -4.85 | | explained_variance | 0.889 | | learning_rate | 0.000243 | | loss | -0.048 | | n_updates | 1364 | | policy_gradient_loss | -0.0287 | | value_loss | 0.00158 | --------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 76.9 | | ep_rew_mean | 0.787 | | time/ | | | fps | 1116 | | iterations | 343 | | time_elapsed | 2515 | | total_timesteps | 2809856 | | train/ | | | approx_kl | 0.100632004 | | clip_fraction | 0.435 | | clip_range | 0.146 | | entropy_loss | -4.86 | | explained_variance | 0.863 | | learning_rate | 0.000243 | | loss | -0.0509 | | n_updates | 1368 | | policy_gradient_loss | -0.0309 | | value_loss | 0.00197 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 79 | | ep_rew_mean | 0.784 | | time/ | | | fps | 1116 | | iterations | 344 | | time_elapsed | 2522 | | total_timesteps | 2818048 | | train/ | | | approx_kl | 0.08695326 | | clip_fraction | 0.47 | | clip_range | 0.146 | | entropy_loss | -5.06 | | explained_variance | 0.892 | | learning_rate | 0.000243 | | loss | -0.0418 | | n_updates | 1372 | | policy_gradient_loss | -0.0325 | | value_loss | 0.00159 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 82 | | ep_rew_mean | 0.773 | | time/ | | | fps | 1117 | | iterations | 345 | | time_elapsed | 2530 | | total_timesteps | 2826240 | | train/ | | | approx_kl | 0.09384805 | | clip_fraction | 0.451 | | clip_range | 0.146 | | entropy_loss | -5.2 | | explained_variance | 0.867 | | learning_rate | 0.000243 | | loss | -0.0388 | | n_updates | 1376 | | policy_gradient_loss | -0.0304 | | value_loss | 0.00197 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 74.9 | | ep_rew_mean | 0.786 | | time/ | | | fps | 1117 | | iterations | 346 | | time_elapsed | 2537 | | total_timesteps | 2834432 | | train/ | | | approx_kl | 0.09023023 | | clip_fraction | 0.466 | | clip_range | 0.146 | | entropy_loss | -5.33 | | explained_variance | 0.886 | | learning_rate | 0.000243 | | loss | -0.0572 | | n_updates | 1380 | | policy_gradient_loss | -0.0352 | | value_loss | 0.00167 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 68.4 | | ep_rew_mean | 0.804 | | time/ | | | fps | 1117 | | iterations | 347 | | time_elapsed | 2544 | | total_timesteps | 2842624 | | train/ | | | approx_kl | 0.09198037 | | clip_fraction | 0.453 | | clip_range | 0.146 | | entropy_loss | -5.1 | | explained_variance | 0.859 | | learning_rate | 0.000243 | | loss | -0.0378 | | n_updates | 1384 | | policy_gradient_loss | -0.0284 | | value_loss | 0.00218 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 69.1 | | ep_rew_mean | 0.802 | | time/ | | | fps | 1117 | | iterations | 348 | | time_elapsed | 2551 | | total_timesteps | 2850816 | | train/ | | | approx_kl | 0.10016458 | | clip_fraction | 0.431 | | clip_range | 0.146 | | entropy_loss | -4.87 | | explained_variance | 0.867 | | learning_rate | 0.000243 | | loss | -0.0328 | | n_updates | 1388 | | policy_gradient_loss | -0.0252 | | value_loss | 0.00199 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 66.5 | | ep_rew_mean | 0.797 | | time/ | | | fps | 1117 | | iterations | 349 | | time_elapsed | 2558 | | total_timesteps | 2859008 | | train/ | | | approx_kl | 0.079433545 | | clip_fraction | 0.438 | | clip_range | 0.146 | | entropy_loss | -4.99 | | explained_variance | 0.908 | | learning_rate | 0.000243 | | loss | -0.0466 | | n_updates | 1392 | | policy_gradient_loss | -0.0303 | | value_loss | 0.00135 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 65.7 | | ep_rew_mean | 0.806 | | time/ | | | fps | 1117 | | iterations | 350 | | time_elapsed | 2565 | | total_timesteps | 2867200 | | train/ | | | approx_kl | 0.09186341 | | clip_fraction | 0.459 | | clip_range | 0.146 | | entropy_loss | -4.94 | | explained_variance | 0.884 | | learning_rate | 0.000243 | | loss | -0.0388 | | n_updates | 1396 | | policy_gradient_loss | -0.029 | | value_loss | 0.00176 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 75.8 | | ep_rew_mean | 0.781 | | time/ | | | fps | 1117 | | iterations | 351 | | time_elapsed | 2572 | | total_timesteps | 2875392 | | train/ | | | approx_kl | 0.10064159 | | clip_fraction | 0.43 | | clip_range | 0.146 | | entropy_loss | -5.03 | | explained_variance | 0.9 | | learning_rate | 0.000243 | | loss | -0.0438 | | n_updates | 1400 | | policy_gradient_loss | -0.0293 | | value_loss | 0.00156 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 65.8 | | ep_rew_mean | 0.809 | | time/ | | | fps | 1117 | | iterations | 352 | | time_elapsed | 2579 | | total_timesteps | 2883584 | | train/ | | | approx_kl | 0.08071382 | | clip_fraction | 0.457 | | clip_range | 0.146 | | entropy_loss | -5.23 | | explained_variance | 0.883 | | learning_rate | 0.000243 | | loss | -0.0489 | | n_updates | 1404 | | policy_gradient_loss | -0.0321 | | value_loss | 0.00179 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 67.1 | | ep_rew_mean | 0.813 | | time/ | | | fps | 1117 | | iterations | 353 | | time_elapsed | 2586 | | total_timesteps | 2891776 | | train/ | | | approx_kl | 0.09713361 | | clip_fraction | 0.449 | | clip_range | 0.146 | | entropy_loss | -4.93 | | explained_variance | 0.882 | | learning_rate | 0.000243 | | loss | -0.0425 | | n_updates | 1408 | | policy_gradient_loss | -0.0295 | | value_loss | 0.00173 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 66.1 | | ep_rew_mean | 0.816 | | time/ | | | fps | 1117 | | iterations | 354 | | time_elapsed | 2593 | | total_timesteps | 2899968 | | train/ | | | approx_kl | 0.117174566 | | clip_fraction | 0.445 | | clip_range | 0.146 | | entropy_loss | -5.09 | | explained_variance | 0.892 | | learning_rate | 0.000243 | | loss | -0.0478 | | n_updates | 1412 | | policy_gradient_loss | -0.031 | | value_loss | 0.00159 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 67.5 | | ep_rew_mean | 0.804 | | time/ | | | fps | 1118 | | iterations | 355 | | time_elapsed | 2601 | | total_timesteps | 2908160 | | train/ | | | approx_kl | 0.07256302 | | clip_fraction | 0.428 | | clip_range | 0.146 | | entropy_loss | -5.08 | | explained_variance | 0.875 | | learning_rate | 0.000243 | | loss | -0.047 | | n_updates | 1416 | | policy_gradient_loss | -0.0265 | | value_loss | 0.00187 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 67.1 | | ep_rew_mean | 0.805 | | time/ | | | fps | 1118 | | iterations | 356 | | time_elapsed | 2608 | | total_timesteps | 2916352 | | train/ | | | approx_kl | 0.08238462 | | clip_fraction | 0.458 | | clip_range | 0.146 | | entropy_loss | -5.17 | | explained_variance | 0.896 | | learning_rate | 0.000243 | | loss | -0.0415 | | n_updates | 1420 | | policy_gradient_loss | -0.0318 | | value_loss | 0.00158 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 64.7 | | ep_rew_mean | 0.813 | | time/ | | | fps | 1118 | | iterations | 357 | | time_elapsed | 2615 | | total_timesteps | 2924544 | | train/ | | | approx_kl | 0.093546055 | | clip_fraction | 0.452 | | clip_range | 0.146 | | entropy_loss | -5.22 | | explained_variance | 0.891 | | learning_rate | 0.000243 | | loss | -0.0378 | | n_updates | 1424 | | policy_gradient_loss | -0.0313 | | value_loss | 0.00162 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 65 | | ep_rew_mean | 0.81 | | time/ | | | fps | 1118 | | iterations | 358 | | time_elapsed | 2621 | | total_timesteps | 2932736 | | train/ | | | approx_kl | 0.105299726 | | clip_fraction | 0.421 | | clip_range | 0.146 | | entropy_loss | -4.94 | | explained_variance | 0.907 | | learning_rate | 0.000243 | | loss | -0.0326 | | n_updates | 1428 | | policy_gradient_loss | -0.0275 | | value_loss | 0.00138 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 61 | | ep_rew_mean | 0.816 | | time/ | | | fps | 1118 | | iterations | 359 | | time_elapsed | 2629 | | total_timesteps | 2940928 | | train/ | | | approx_kl | 0.090708524 | | clip_fraction | 0.432 | | clip_range | 0.146 | | entropy_loss | -4.81 | | explained_variance | 0.906 | | learning_rate | 0.000243 | | loss | -0.0294 | | n_updates | 1432 | | policy_gradient_loss | -0.0281 | | value_loss | 0.00133 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 65.6 | | ep_rew_mean | 0.808 | | time/ | | | fps | 1118 | | iterations | 360 | | time_elapsed | 2636 | | total_timesteps | 2949120 | | train/ | | | approx_kl | 0.08802066 | | clip_fraction | 0.454 | | clip_range | 0.146 | | entropy_loss | -4.77 | | explained_variance | 0.924 | | learning_rate | 0.000243 | | loss | -0.0476 | | n_updates | 1436 | | policy_gradient_loss | -0.0275 | | value_loss | 0.00111 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 63.4 | | ep_rew_mean | 0.817 | | time/ | | | fps | 1118 | | iterations | 361 | | time_elapsed | 2643 | | total_timesteps | 2957312 | | train/ | | | approx_kl | 0.08810686 | | clip_fraction | 0.452 | | clip_range | 0.146 | | entropy_loss | -5 | | explained_variance | 0.903 | | learning_rate | 0.000243 | | loss | -0.0462 | | n_updates | 1440 | | policy_gradient_loss | -0.0289 | | value_loss | 0.00144 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 64.1 | | ep_rew_mean | 0.807 | | time/ | | | fps | 1119 | | iterations | 362 | | time_elapsed | 2650 | | total_timesteps | 2965504 | | train/ | | | approx_kl | 0.092682995 | | clip_fraction | 0.432 | | clip_range | 0.146 | | entropy_loss | -4.91 | | explained_variance | 0.902 | | learning_rate | 0.000243 | | loss | -0.0343 | | n_updates | 1444 | | policy_gradient_loss | -0.0268 | | value_loss | 0.00141 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 75.2 | | ep_rew_mean | 0.792 | | time/ | | | fps | 1119 | | iterations | 363 | | time_elapsed | 2657 | | total_timesteps | 2973696 | | train/ | | | approx_kl | 0.083926834 | | clip_fraction | 0.454 | | clip_range | 0.146 | | entropy_loss | -5 | | explained_variance | 0.903 | | learning_rate | 0.000243 | | loss | -0.0395 | | n_updates | 1448 | | policy_gradient_loss | -0.0291 | | value_loss | 0.00144 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 71.9 | | ep_rew_mean | 0.783 | | time/ | | | fps | 1119 | | iterations | 364 | | time_elapsed | 2663 | | total_timesteps | 2981888 | | train/ | | | approx_kl | 0.07594952 | | clip_fraction | 0.459 | | clip_range | 0.146 | | entropy_loss | -5.34 | | explained_variance | 0.876 | | learning_rate | 0.000243 | | loss | -0.0485 | | n_updates | 1452 | | policy_gradient_loss | -0.0332 | | value_loss | 0.00185 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 65 | | ep_rew_mean | 0.8 | | time/ | | | fps | 1119 | | iterations | 365 | | time_elapsed | 2671 | | total_timesteps | 2990080 | | train/ | | | approx_kl | 0.084617056 | | clip_fraction | 0.433 | | clip_range | 0.146 | | entropy_loss | -5.23 | | explained_variance | 0.902 | | learning_rate | 0.000243 | | loss | -0.0449 | | n_updates | 1456 | | policy_gradient_loss | -0.0324 | | value_loss | 0.00145 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 69.2 | | ep_rew_mean | 0.796 | | time/ | | | fps | 1119 | | iterations | 366 | | time_elapsed | 2678 | | total_timesteps | 2998272 | | train/ | | | approx_kl | 0.091500655 | | clip_fraction | 0.46 | | clip_range | 0.146 | | entropy_loss | -5.06 | | explained_variance | 0.893 | | learning_rate | 0.000243 | | loss | -0.0367 | | n_updates | 1460 | | policy_gradient_loss | -0.0301 | | value_loss | 0.00155 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 59.9 | | ep_rew_mean | 0.826 | | time/ | | | fps | 1119 | | iterations | 367 | | time_elapsed | 2685 | | total_timesteps | 3006464 | | train/ | | | approx_kl | 0.08061509 | | clip_fraction | 0.437 | | clip_range | 0.146 | | entropy_loss | -5.22 | | explained_variance | 0.897 | | learning_rate | 0.000243 | | loss | -0.04 | | n_updates | 1464 | | policy_gradient_loss | -0.0293 | | value_loss | 0.00156 | ---------------------------------------- --------------------------------------- | rollout/ | | | ep_len_mean | 64.3 | | ep_rew_mean | 0.815 | | time/ | | | fps | 1119 | | iterations | 368 | | time_elapsed | 2692 | | total_timesteps | 3014656 | | train/ | | | approx_kl | 0.0826277 | | clip_fraction | 0.383 | | clip_range | 0.146 | | entropy_loss | -4.84 | | explained_variance | 0.92 | | learning_rate | 0.000243 | | loss | -0.0258 | | n_updates | 1468 | | policy_gradient_loss | -0.0231 | | value_loss | 0.00101 | --------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 53.8 | | ep_rew_mean | 0.833 | | time/ | | | fps | 1119 | | iterations | 369 | | time_elapsed | 2699 | | total_timesteps | 3022848 | | train/ | | | approx_kl | 0.06985395 | | clip_fraction | 0.403 | | clip_range | 0.146 | | entropy_loss | -5.11 | | explained_variance | 0.874 | | learning_rate | 0.000243 | | loss | -0.0361 | | n_updates | 1472 | | policy_gradient_loss | -0.0253 | | value_loss | 0.00168 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 59 | | ep_rew_mean | 0.822 | | time/ | | | fps | 1119 | | iterations | 370 | | time_elapsed | 2706 | | total_timesteps | 3031040 | | train/ | | | approx_kl | 0.09784728 | | clip_fraction | 0.416 | | clip_range | 0.146 | | entropy_loss | -4.77 | | explained_variance | 0.907 | | learning_rate | 0.000243 | | loss | -0.0345 | | n_updates | 1476 | | policy_gradient_loss | -0.0218 | | value_loss | 0.00106 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 56.8 | | ep_rew_mean | 0.819 | | time/ | | | fps | 1119 | | iterations | 371 | | time_elapsed | 2713 | | total_timesteps | 3039232 | | train/ | | | approx_kl | 0.10295618 | | clip_fraction | 0.402 | | clip_range | 0.146 | | entropy_loss | -5.03 | | explained_variance | 0.91 | | learning_rate | 0.000242 | | loss | -0.0366 | | n_updates | 1480 | | policy_gradient_loss | -0.0295 | | value_loss | 0.00118 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 62.9 | | ep_rew_mean | 0.816 | | time/ | | | fps | 1119 | | iterations | 372 | | time_elapsed | 2720 | | total_timesteps | 3047424 | | train/ | | | approx_kl | 0.07214656 | | clip_fraction | 0.419 | | clip_range | 0.146 | | entropy_loss | -4.86 | | explained_variance | 0.91 | | learning_rate | 0.000242 | | loss | -0.0369 | | n_updates | 1484 | | policy_gradient_loss | -0.0227 | | value_loss | 0.0011 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 77 | | ep_rew_mean | 0.778 | | time/ | | | fps | 1120 | | iterations | 373 | | time_elapsed | 2728 | | total_timesteps | 3055616 | | train/ | | | approx_kl | 0.08703825 | | clip_fraction | 0.449 | | clip_range | 0.146 | | entropy_loss | -5.14 | | explained_variance | 0.928 | | learning_rate | 0.000242 | | loss | -0.0393 | | n_updates | 1488 | | policy_gradient_loss | -0.0268 | | value_loss | 0.00114 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 79.3 | | ep_rew_mean | 0.78 | | time/ | | | fps | 1120 | | iterations | 374 | | time_elapsed | 2735 | | total_timesteps | 3063808 | | train/ | | | approx_kl | 0.09813295 | | clip_fraction | 0.477 | | clip_range | 0.146 | | entropy_loss | -5.44 | | explained_variance | 0.911 | | learning_rate | 0.000242 | | loss | -0.0523 | | n_updates | 1492 | | policy_gradient_loss | -0.0349 | | value_loss | 0.00144 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 62 | | ep_rew_mean | 0.815 | | time/ | | | fps | 1120 | | iterations | 375 | | time_elapsed | 2742 | | total_timesteps | 3072000 | | train/ | | | approx_kl | 0.101370454 | | clip_fraction | 0.451 | | clip_range | 0.146 | | entropy_loss | -5.49 | | explained_variance | 0.914 | | learning_rate | 0.000242 | | loss | -0.0362 | | n_updates | 1496 | | policy_gradient_loss | -0.0316 | | value_loss | 0.0014 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 65.5 | | ep_rew_mean | 0.794 | | time/ | | | fps | 1120 | | iterations | 376 | | time_elapsed | 2749 | | total_timesteps | 3080192 | | train/ | | | approx_kl | 0.09665693 | | clip_fraction | 0.431 | | clip_range | 0.146 | | entropy_loss | -5.17 | | explained_variance | 0.899 | | learning_rate | 0.000242 | | loss | -0.037 | | n_updates | 1500 | | policy_gradient_loss | -0.0263 | | value_loss | 0.00149 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 57 | | ep_rew_mean | 0.832 | | time/ | | | fps | 1120 | | iterations | 377 | | time_elapsed | 2756 | | total_timesteps | 3088384 | | train/ | | | approx_kl | 0.07535775 | | clip_fraction | 0.444 | | clip_range | 0.146 | | entropy_loss | -5.29 | | explained_variance | 0.915 | | learning_rate | 0.000242 | | loss | -0.0549 | | n_updates | 1504 | | policy_gradient_loss | -0.0311 | | value_loss | 0.00128 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 54.6 | | ep_rew_mean | 0.833 | | time/ | | | fps | 1120 | | iterations | 378 | | time_elapsed | 2763 | | total_timesteps | 3096576 | | train/ | | | approx_kl | 0.09817378 | | clip_fraction | 0.409 | | clip_range | 0.146 | | entropy_loss | -4.9 | | explained_variance | 0.933 | | learning_rate | 0.000242 | | loss | -0.0391 | | n_updates | 1508 | | policy_gradient_loss | -0.026 | | value_loss | 0.000875 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 59.8 | | ep_rew_mean | 0.823 | | time/ | | | fps | 1120 | | iterations | 379 | | time_elapsed | 2771 | | total_timesteps | 3104768 | | train/ | | | approx_kl | 0.10071172 | | clip_fraction | 0.4 | | clip_range | 0.146 | | entropy_loss | -4.8 | | explained_variance | 0.897 | | learning_rate | 0.000242 | | loss | -0.0247 | | n_updates | 1512 | | policy_gradient_loss | -0.0193 | | value_loss | 0.00125 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 53 | | ep_rew_mean | 0.833 | | time/ | | | fps | 1120 | | iterations | 380 | | time_elapsed | 2777 | | total_timesteps | 3112960 | | train/ | | | approx_kl | 0.07438055 | | clip_fraction | 0.37 | | clip_range | 0.146 | | entropy_loss | -4.74 | | explained_variance | 0.933 | | learning_rate | 0.000242 | | loss | -0.0314 | | n_updates | 1516 | | policy_gradient_loss | -0.0222 | | value_loss | 0.000765 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 53.3 | | ep_rew_mean | 0.833 | | time/ | | | fps | 1120 | | iterations | 381 | | time_elapsed | 2784 | | total_timesteps | 3121152 | | train/ | | | approx_kl | 0.070820585 | | clip_fraction | 0.419 | | clip_range | 0.146 | | entropy_loss | -4.58 | | explained_variance | 0.948 | | learning_rate | 0.000242 | | loss | -0.0274 | | n_updates | 1520 | | policy_gradient_loss | -0.0181 | | value_loss | 0.000562 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 57.1 | | ep_rew_mean | 0.833 | | time/ | | | fps | 1120 | | iterations | 382 | | time_elapsed | 2792 | | total_timesteps | 3129344 | | train/ | | | approx_kl | 0.08813757 | | clip_fraction | 0.392 | | clip_range | 0.146 | | entropy_loss | -4.66 | | explained_variance | 0.934 | | learning_rate | 0.000242 | | loss | -0.0248 | | n_updates | 1524 | | policy_gradient_loss | -0.0208 | | value_loss | 0.000786 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 50.8 | | ep_rew_mean | 0.845 | | time/ | | | fps | 1120 | | iterations | 383 | | time_elapsed | 2799 | | total_timesteps | 3137536 | | train/ | | | approx_kl | 0.09866084 | | clip_fraction | 0.387 | | clip_range | 0.146 | | entropy_loss | -4.8 | | explained_variance | 0.904 | | learning_rate | 0.000242 | | loss | -0.0304 | | n_updates | 1528 | | policy_gradient_loss | -0.0227 | | value_loss | 0.00117 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 57.5 | | ep_rew_mean | 0.832 | | time/ | | | fps | 1121 | | iterations | 384 | | time_elapsed | 2806 | | total_timesteps | 3145728 | | train/ | | | approx_kl | 0.08429769 | | clip_fraction | 0.352 | | clip_range | 0.146 | | entropy_loss | -4.63 | | explained_variance | 0.942 | | learning_rate | 0.000242 | | loss | -0.0229 | | n_updates | 1532 | | policy_gradient_loss | -0.022 | | value_loss | 0.00057 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 55.7 | | ep_rew_mean | 0.828 | | time/ | | | fps | 1121 | | iterations | 385 | | time_elapsed | 2813 | | total_timesteps | 3153920 | | train/ | | | approx_kl | 0.08888651 | | clip_fraction | 0.402 | | clip_range | 0.146 | | entropy_loss | -4.86 | | explained_variance | 0.928 | | learning_rate | 0.000242 | | loss | -0.0331 | | n_updates | 1536 | | policy_gradient_loss | -0.0246 | | value_loss | 0.000919 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 50.6 | | ep_rew_mean | 0.837 | | time/ | | | fps | 1121 | | iterations | 386 | | time_elapsed | 2820 | | total_timesteps | 3162112 | | train/ | | | approx_kl | 0.08318235 | | clip_fraction | 0.431 | | clip_range | 0.146 | | entropy_loss | -4.84 | | explained_variance | 0.902 | | learning_rate | 0.000242 | | loss | -0.0369 | | n_updates | 1540 | | policy_gradient_loss | -0.0245 | | value_loss | 0.0012 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 51.6 | | ep_rew_mean | 0.837 | | time/ | | | fps | 1121 | | iterations | 387 | | time_elapsed | 2827 | | total_timesteps | 3170304 | | train/ | | | approx_kl | 0.07106483 | | clip_fraction | 0.371 | | clip_range | 0.146 | | entropy_loss | -4.74 | | explained_variance | 0.912 | | learning_rate | 0.000242 | | loss | -0.0266 | | n_updates | 1544 | | policy_gradient_loss | -0.0212 | | value_loss | 0.00099 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 60.7 | | ep_rew_mean | 0.818 | | time/ | | | fps | 1121 | | iterations | 388 | | time_elapsed | 2834 | | total_timesteps | 3178496 | | train/ | | | approx_kl | 0.07996462 | | clip_fraction | 0.365 | | clip_range | 0.146 | | entropy_loss | -4.88 | | explained_variance | 0.902 | | learning_rate | 0.000242 | | loss | -0.0355 | | n_updates | 1548 | | policy_gradient_loss | -0.0228 | | value_loss | 0.00111 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 57.5 | | ep_rew_mean | 0.823 | | time/ | | | fps | 1121 | | iterations | 389 | | time_elapsed | 2841 | | total_timesteps | 3186688 | | train/ | | | approx_kl | 0.08551867 | | clip_fraction | 0.403 | | clip_range | 0.146 | | entropy_loss | -5.05 | | explained_variance | 0.884 | | learning_rate | 0.000242 | | loss | -0.0382 | | n_updates | 1552 | | policy_gradient_loss | -0.0293 | | value_loss | 0.00154 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 61.3 | | ep_rew_mean | 0.821 | | time/ | | | fps | 1121 | | iterations | 390 | | time_elapsed | 2848 | | total_timesteps | 3194880 | | train/ | | | approx_kl | 0.059828844 | | clip_fraction | 0.397 | | clip_range | 0.146 | | entropy_loss | -5.15 | | explained_variance | 0.909 | | learning_rate | 0.000242 | | loss | -0.0329 | | n_updates | 1556 | | policy_gradient_loss | -0.0224 | | value_loss | 0.00127 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 57.3 | | ep_rew_mean | 0.825 | | time/ | | | fps | 1121 | | iterations | 391 | | time_elapsed | 2855 | | total_timesteps | 3203072 | | train/ | | | approx_kl | 0.115995586 | | clip_fraction | 0.42 | | clip_range | 0.146 | | entropy_loss | -5.24 | | explained_variance | 0.923 | | learning_rate | 0.000242 | | loss | -0.0417 | | n_updates | 1560 | | policy_gradient_loss | -0.0309 | | value_loss | 0.00115 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 51.5 | | ep_rew_mean | 0.846 | | time/ | | | fps | 1121 | | iterations | 392 | | time_elapsed | 2862 | | total_timesteps | 3211264 | | train/ | | | approx_kl | 0.06558256 | | clip_fraction | 0.381 | | clip_range | 0.146 | | entropy_loss | -5.02 | | explained_variance | 0.934 | | learning_rate | 0.000242 | | loss | -0.0424 | | n_updates | 1564 | | policy_gradient_loss | -0.0248 | | value_loss | 0.000854 | ---------------------------------------- --------------------------------------- | rollout/ | | | ep_len_mean | 56.5 | | ep_rew_mean | 0.824 | | time/ | | | fps | 1121 | | iterations | 393 | | time_elapsed | 2870 | | total_timesteps | 3219456 | | train/ | | | approx_kl | 0.0746405 | | clip_fraction | 0.359 | | clip_range | 0.146 | | entropy_loss | -4.98 | | explained_variance | 0.889 | | learning_rate | 0.000242 | | loss | -0.0354 | | n_updates | 1568 | | policy_gradient_loss | -0.0203 | | value_loss | 0.00122 | --------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 53.9 | | ep_rew_mean | 0.828 | | time/ | | | fps | 1121 | | iterations | 394 | | time_elapsed | 2877 | | total_timesteps | 3227648 | | train/ | | | approx_kl | 0.070231065 | | clip_fraction | 0.395 | | clip_range | 0.146 | | entropy_loss | -5.06 | | explained_variance | 0.894 | | learning_rate | 0.000242 | | loss | -0.0112 | | n_updates | 1572 | | policy_gradient_loss | -0.0238 | | value_loss | 0.00132 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 63.2 | | ep_rew_mean | 0.821 | | time/ | | | fps | 1121 | | iterations | 395 | | time_elapsed | 2884 | | total_timesteps | 3235840 | | train/ | | | approx_kl | 0.097267956 | | clip_fraction | 0.367 | | clip_range | 0.146 | | entropy_loss | -5.11 | | explained_variance | 0.905 | | learning_rate | 0.000242 | | loss | -0.0358 | | n_updates | 1576 | | policy_gradient_loss | -0.0265 | | value_loss | 0.00123 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 56.5 | | ep_rew_mean | 0.834 | | time/ | | | fps | 1121 | | iterations | 396 | | time_elapsed | 2891 | | total_timesteps | 3244032 | | train/ | | | approx_kl | 0.09271029 | | clip_fraction | 0.405 | | clip_range | 0.146 | | entropy_loss | -5.3 | | explained_variance | 0.914 | | learning_rate | 0.000242 | | loss | -0.0377 | | n_updates | 1580 | | policy_gradient_loss | -0.0314 | | value_loss | 0.00126 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 54.2 | | ep_rew_mean | 0.838 | | time/ | | | fps | 1121 | | iterations | 397 | | time_elapsed | 2898 | | total_timesteps | 3252224 | | train/ | | | approx_kl | 0.08296621 | | clip_fraction | 0.391 | | clip_range | 0.146 | | entropy_loss | -5.08 | | explained_variance | 0.927 | | learning_rate | 0.000242 | | loss | -0.0338 | | n_updates | 1584 | | policy_gradient_loss | -0.0251 | | value_loss | 0.000938 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 53.3 | | ep_rew_mean | 0.841 | | time/ | | | fps | 1122 | | iterations | 398 | | time_elapsed | 2905 | | total_timesteps | 3260416 | | train/ | | | approx_kl | 0.076973185 | | clip_fraction | 0.381 | | clip_range | 0.146 | | entropy_loss | -4.97 | | explained_variance | 0.932 | | learning_rate | 0.000242 | | loss | -0.0327 | | n_updates | 1588 | | policy_gradient_loss | -0.0214 | | value_loss | 0.000685 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 57.6 | | ep_rew_mean | 0.827 | | time/ | | | fps | 1122 | | iterations | 399 | | time_elapsed | 2912 | | total_timesteps | 3268608 | | train/ | | | approx_kl | 0.08231124 | | clip_fraction | 0.367 | | clip_range | 0.146 | | entropy_loss | -5.08 | | explained_variance | 0.911 | | learning_rate | 0.000242 | | loss | -0.028 | | n_updates | 1592 | | policy_gradient_loss | -0.0209 | | value_loss | 0.00105 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 57.7 | | ep_rew_mean | 0.815 | | time/ | | | fps | 1122 | | iterations | 400 | | time_elapsed | 2920 | | total_timesteps | 3276800 | | train/ | | | approx_kl | 0.08599094 | | clip_fraction | 0.416 | | clip_range | 0.146 | | entropy_loss | -5.22 | | explained_variance | 0.935 | | learning_rate | 0.000242 | | loss | -0.0477 | | n_updates | 1596 | | policy_gradient_loss | -0.0295 | | value_loss | 0.000957 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 56.9 | | ep_rew_mean | 0.829 | | time/ | | | fps | 1122 | | iterations | 401 | | time_elapsed | 2927 | | total_timesteps | 3284992 | | train/ | | | approx_kl | 0.076907575 | | clip_fraction | 0.377 | | clip_range | 0.146 | | entropy_loss | -5.02 | | explained_variance | 0.952 | | learning_rate | 0.000242 | | loss | -0.0246 | | n_updates | 1600 | | policy_gradient_loss | -0.0254 | | value_loss | 0.000677 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 52.2 | | ep_rew_mean | 0.838 | | time/ | | | fps | 1122 | | iterations | 402 | | time_elapsed | 2934 | | total_timesteps | 3293184 | | train/ | | | approx_kl | 0.07774804 | | clip_fraction | 0.428 | | clip_range | 0.146 | | entropy_loss | -5.04 | | explained_variance | 0.922 | | learning_rate | 0.000242 | | loss | -0.0321 | | n_updates | 1604 | | policy_gradient_loss | -0.0223 | | value_loss | 0.00104 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 55.5 | | ep_rew_mean | 0.831 | | time/ | | | fps | 1122 | | iterations | 403 | | time_elapsed | 2941 | | total_timesteps | 3301376 | | train/ | | | approx_kl | 0.074767835 | | clip_fraction | 0.376 | | clip_range | 0.146 | | entropy_loss | -4.89 | | explained_variance | 0.919 | | learning_rate | 0.000242 | | loss | -0.0194 | | n_updates | 1608 | | policy_gradient_loss | -0.02 | | value_loss | 0.000954 | ----------------------------------------- -------------------------------------- | rollout/ | | | ep_len_mean | 60 | | ep_rew_mean | 0.828 | | time/ | | | fps | 1122 | | iterations | 404 | | time_elapsed | 2948 | | total_timesteps | 3309568 | | train/ | | | approx_kl | 0.091023 | | clip_fraction | 0.358 | | clip_range | 0.146 | | entropy_loss | -4.97 | | explained_variance | 0.934 | | learning_rate | 0.000242 | | loss | -0.0291 | | n_updates | 1612 | | policy_gradient_loss | -0.0209 | | value_loss | 0.000821 | -------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 49.8 | | ep_rew_mean | 0.848 | | time/ | | | fps | 1122 | | iterations | 405 | | time_elapsed | 2955 | | total_timesteps | 3317760 | | train/ | | | approx_kl | 0.08699921 | | clip_fraction | 0.379 | | clip_range | 0.146 | | entropy_loss | -5.06 | | explained_variance | 0.916 | | learning_rate | 0.000242 | | loss | -0.0402 | | n_updates | 1616 | | policy_gradient_loss | -0.0236 | | value_loss | 0.0011 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 54.8 | | ep_rew_mean | 0.834 | | time/ | | | fps | 1122 | | iterations | 406 | | time_elapsed | 2962 | | total_timesteps | 3325952 | | train/ | | | approx_kl | 0.07301657 | | clip_fraction | 0.363 | | clip_range | 0.146 | | entropy_loss | -5.01 | | explained_variance | 0.908 | | learning_rate | 0.000242 | | loss | -0.0235 | | n_updates | 1620 | | policy_gradient_loss | -0.0207 | | value_loss | 0.00097 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 65.9 | | ep_rew_mean | 0.807 | | time/ | | | fps | 1122 | | iterations | 407 | | time_elapsed | 2969 | | total_timesteps | 3334144 | | train/ | | | approx_kl | 0.086166784 | | clip_fraction | 0.367 | | clip_range | 0.146 | | entropy_loss | -5.04 | | explained_variance | 0.913 | | learning_rate | 0.000242 | | loss | -0.0187 | | n_updates | 1624 | | policy_gradient_loss | -0.0231 | | value_loss | 0.00104 | ----------------------------------------- -------------------------------------- | rollout/ | | | ep_len_mean | 63.7 | | ep_rew_mean | 0.807 | | time/ | | | fps | 1122 | | iterations | 408 | | time_elapsed | 2976 | | total_timesteps | 3342336 | | train/ | | | approx_kl | 0.092338 | | clip_fraction | 0.427 | | clip_range | 0.146 | | entropy_loss | -5.31 | | explained_variance | 0.939 | | learning_rate | 0.000242 | | loss | -0.0464 | | n_updates | 1628 | | policy_gradient_loss | -0.0323 | | value_loss | 0.000928 | -------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 55.3 | | ep_rew_mean | 0.82 | | time/ | | | fps | 1122 | | iterations | 409 | | time_elapsed | 2983 | | total_timesteps | 3350528 | | train/ | | | approx_kl | 0.07773994 | | clip_fraction | 0.386 | | clip_range | 0.146 | | entropy_loss | -5.2 | | explained_variance | 0.9 | | learning_rate | 0.000242 | | loss | -0.0304 | | n_updates | 1632 | | policy_gradient_loss | -0.023 | | value_loss | 0.00145 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 58.6 | | ep_rew_mean | 0.823 | | time/ | | | fps | 1123 | | iterations | 410 | | time_elapsed | 2990 | | total_timesteps | 3358720 | | train/ | | | approx_kl | 0.10200008 | | clip_fraction | 0.41 | | clip_range | 0.146 | | entropy_loss | -5.03 | | explained_variance | 0.898 | | learning_rate | 0.000242 | | loss | -0.0194 | | n_updates | 1636 | | policy_gradient_loss | -0.0224 | | value_loss | 0.00133 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 52.2 | | ep_rew_mean | 0.845 | | time/ | | | fps | 1123 | | iterations | 411 | | time_elapsed | 2997 | | total_timesteps | 3366912 | | train/ | | | approx_kl | 0.083237424 | | clip_fraction | 0.379 | | clip_range | 0.146 | | entropy_loss | -5.08 | | explained_variance | 0.937 | | learning_rate | 0.000242 | | loss | -0.0403 | | n_updates | 1640 | | policy_gradient_loss | -0.0265 | | value_loss | 0.000767 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 50.8 | | ep_rew_mean | 0.845 | | time/ | | | fps | 1123 | | iterations | 412 | | time_elapsed | 3004 | | total_timesteps | 3375104 | | train/ | | | approx_kl | 0.06891382 | | clip_fraction | 0.363 | | clip_range | 0.146 | | entropy_loss | -4.76 | | explained_variance | 0.928 | | learning_rate | 0.000242 | | loss | -0.0269 | | n_updates | 1644 | | policy_gradient_loss | -0.0181 | | value_loss | 0.000699 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 51 | | ep_rew_mean | 0.844 | | time/ | | | fps | 1123 | | iterations | 413 | | time_elapsed | 3011 | | total_timesteps | 3383296 | | train/ | | | approx_kl | 0.09043713 | | clip_fraction | 0.338 | | clip_range | 0.146 | | entropy_loss | -4.7 | | explained_variance | 0.939 | | learning_rate | 0.000242 | | loss | -0.0119 | | n_updates | 1648 | | policy_gradient_loss | -0.0137 | | value_loss | 0.000504 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 56.2 | | ep_rew_mean | 0.839 | | time/ | | | fps | 1123 | | iterations | 414 | | time_elapsed | 3018 | | total_timesteps | 3391488 | | train/ | | | approx_kl | 0.08183843 | | clip_fraction | 0.383 | | clip_range | 0.146 | | entropy_loss | -4.8 | | explained_variance | 0.917 | | learning_rate | 0.000242 | | loss | -0.0363 | | n_updates | 1652 | | policy_gradient_loss | -0.0211 | | value_loss | 0.000826 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 60.5 | | ep_rew_mean | 0.817 | | time/ | | | fps | 1123 | | iterations | 415 | | time_elapsed | 3026 | | total_timesteps | 3399680 | | train/ | | | approx_kl | 0.065963894 | | clip_fraction | 0.374 | | clip_range | 0.146 | | entropy_loss | -4.87 | | explained_variance | 0.914 | | learning_rate | 0.000242 | | loss | -0.0267 | | n_updates | 1656 | | policy_gradient_loss | -0.0191 | | value_loss | 0.000986 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 51.1 | | ep_rew_mean | 0.839 | | time/ | | | fps | 1123 | | iterations | 416 | | time_elapsed | 3033 | | total_timesteps | 3407872 | | train/ | | | approx_kl | 0.07462531 | | clip_fraction | 0.394 | | clip_range | 0.146 | | entropy_loss | -5.01 | | explained_variance | 0.923 | | learning_rate | 0.000242 | | loss | -0.0342 | | n_updates | 1660 | | policy_gradient_loss | -0.0271 | | value_loss | 0.000912 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 49.3 | | ep_rew_mean | 0.843 | | time/ | | | fps | 1123 | | iterations | 417 | | time_elapsed | 3040 | | total_timesteps | 3416064 | | train/ | | | approx_kl | 0.071058095 | | clip_fraction | 0.362 | | clip_range | 0.146 | | entropy_loss | -4.75 | | explained_variance | 0.912 | | learning_rate | 0.000242 | | loss | -0.0244 | | n_updates | 1664 | | policy_gradient_loss | -0.0166 | | value_loss | 0.000865 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 53.2 | | ep_rew_mean | 0.827 | | time/ | | | fps | 1123 | | iterations | 418 | | time_elapsed | 3047 | | total_timesteps | 3424256 | | train/ | | | approx_kl | 0.04773946 | | clip_fraction | 0.303 | | clip_range | 0.146 | | entropy_loss | -4.65 | | explained_variance | 0.958 | | learning_rate | 0.000242 | | loss | -0.00931 | | n_updates | 1668 | | policy_gradient_loss | -0.0124 | | value_loss | 0.000327 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 51.4 | | ep_rew_mean | 0.845 | | time/ | | | fps | 1123 | | iterations | 419 | | time_elapsed | 3054 | | total_timesteps | 3432448 | | train/ | | | approx_kl | 0.11068389 | | clip_fraction | 0.358 | | clip_range | 0.146 | | entropy_loss | -4.83 | | explained_variance | 0.913 | | learning_rate | 0.000242 | | loss | -0.0271 | | n_updates | 1672 | | policy_gradient_loss | -0.0214 | | value_loss | 0.000953 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 47.6 | | ep_rew_mean | 0.848 | | time/ | | | fps | 1123 | | iterations | 420 | | time_elapsed | 3061 | | total_timesteps | 3440640 | | train/ | | | approx_kl | 0.09036707 | | clip_fraction | 0.334 | | clip_range | 0.146 | | entropy_loss | -4.7 | | explained_variance | 0.892 | | learning_rate | 0.000242 | | loss | -0.0213 | | n_updates | 1676 | | policy_gradient_loss | -0.0177 | | value_loss | 0.000996 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 53.5 | | ep_rew_mean | 0.829 | | time/ | | | fps | 1123 | | iterations | 421 | | time_elapsed | 3068 | | total_timesteps | 3448832 | | train/ | | | approx_kl | 0.05051452 | | clip_fraction | 0.272 | | clip_range | 0.146 | | entropy_loss | -4.63 | | explained_variance | 0.937 | | learning_rate | 0.000241 | | loss | -0.0135 | | n_updates | 1680 | | policy_gradient_loss | -0.0113 | | value_loss | 0.000395 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 49.2 | | ep_rew_mean | 0.844 | | time/ | | | fps | 1123 | | iterations | 422 | | time_elapsed | 3075 | | total_timesteps | 3457024 | | train/ | | | approx_kl | 0.07125251 | | clip_fraction | 0.374 | | clip_range | 0.146 | | entropy_loss | -4.76 | | explained_variance | 0.923 | | learning_rate | 0.000241 | | loss | -0.0259 | | n_updates | 1684 | | policy_gradient_loss | -0.021 | | value_loss | 0.000789 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 47.6 | | ep_rew_mean | 0.85 | | time/ | | | fps | 1123 | | iterations | 423 | | time_elapsed | 3083 | | total_timesteps | 3465216 | | train/ | | | approx_kl | 0.07593008 | | clip_fraction | 0.341 | | clip_range | 0.146 | | entropy_loss | -4.67 | | explained_variance | 0.955 | | learning_rate | 0.000241 | | loss | -0.0219 | | n_updates | 1688 | | policy_gradient_loss | -0.0157 | | value_loss | 0.000404 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 53.5 | | ep_rew_mean | 0.843 | | time/ | | | fps | 1124 | | iterations | 424 | | time_elapsed | 3090 | | total_timesteps | 3473408 | | train/ | | | approx_kl | 0.07231134 | | clip_fraction | 0.329 | | clip_range | 0.146 | | entropy_loss | -4.7 | | explained_variance | 0.954 | | learning_rate | 0.000241 | | loss | -0.0128 | | n_updates | 1692 | | policy_gradient_loss | -0.0154 | | value_loss | 0.000417 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 49 | | ep_rew_mean | 0.846 | | time/ | | | fps | 1124 | | iterations | 425 | | time_elapsed | 3097 | | total_timesteps | 3481600 | | train/ | | | approx_kl | 0.08497012 | | clip_fraction | 0.352 | | clip_range | 0.146 | | entropy_loss | -4.81 | | explained_variance | 0.937 | | learning_rate | 0.000241 | | loss | -0.0271 | | n_updates | 1696 | | policy_gradient_loss | -0.0215 | | value_loss | 0.000643 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 57.1 | | ep_rew_mean | 0.831 | | time/ | | | fps | 1124 | | iterations | 426 | | time_elapsed | 3104 | | total_timesteps | 3489792 | | train/ | | | approx_kl | 0.056607023 | | clip_fraction | 0.378 | | clip_range | 0.146 | | entropy_loss | -4.81 | | explained_variance | 0.941 | | learning_rate | 0.000241 | | loss | -0.0276 | | n_updates | 1700 | | policy_gradient_loss | -0.0181 | | value_loss | 0.000594 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 54.8 | | ep_rew_mean | 0.831 | | time/ | | | fps | 1124 | | iterations | 427 | | time_elapsed | 3111 | | total_timesteps | 3497984 | | train/ | | | approx_kl | 0.08374736 | | clip_fraction | 0.366 | | clip_range | 0.146 | | entropy_loss | -4.96 | | explained_variance | 0.929 | | learning_rate | 0.000241 | | loss | -0.035 | | n_updates | 1704 | | policy_gradient_loss | -0.0248 | | value_loss | 0.000807 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 54.5 | | ep_rew_mean | 0.839 | | time/ | | | fps | 1124 | | iterations | 428 | | time_elapsed | 3118 | | total_timesteps | 3506176 | | train/ | | | approx_kl | 0.09215112 | | clip_fraction | 0.365 | | clip_range | 0.146 | | entropy_loss | -4.92 | | explained_variance | 0.91 | | learning_rate | 0.000241 | | loss | -0.0343 | | n_updates | 1708 | | policy_gradient_loss | -0.0218 | | value_loss | 0.00106 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 52.6 | | ep_rew_mean | 0.835 | | time/ | | | fps | 1124 | | iterations | 429 | | time_elapsed | 3125 | | total_timesteps | 3514368 | | train/ | | | approx_kl | 0.06682532 | | clip_fraction | 0.324 | | clip_range | 0.146 | | entropy_loss | -4.85 | | explained_variance | 0.904 | | learning_rate | 0.000241 | | loss | -0.026 | | n_updates | 1712 | | policy_gradient_loss | -0.0202 | | value_loss | 0.000973 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 51.2 | | ep_rew_mean | 0.833 | | time/ | | | fps | 1124 | | iterations | 430 | | time_elapsed | 3133 | | total_timesteps | 3522560 | | train/ | | | approx_kl | 0.072802305 | | clip_fraction | 0.355 | | clip_range | 0.146 | | entropy_loss | -4.8 | | explained_variance | 0.962 | | learning_rate | 0.000241 | | loss | -0.0343 | | n_updates | 1716 | | policy_gradient_loss | -0.0235 | | value_loss | 0.00041 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 47.4 | | ep_rew_mean | 0.846 | | time/ | | | fps | 1124 | | iterations | 431 | | time_elapsed | 3139 | | total_timesteps | 3530752 | | train/ | | | approx_kl | 0.10327864 | | clip_fraction | 0.334 | | clip_range | 0.146 | | entropy_loss | -4.79 | | explained_variance | 0.951 | | learning_rate | 0.000241 | | loss | -0.0368 | | n_updates | 1720 | | policy_gradient_loss | -0.0205 | | value_loss | 0.00052 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 48.2 | | ep_rew_mean | 0.842 | | time/ | | | fps | 1124 | | iterations | 432 | | time_elapsed | 3146 | | total_timesteps | 3538944 | | train/ | | | approx_kl | 0.07062249 | | clip_fraction | 0.341 | | clip_range | 0.146 | | entropy_loss | -4.71 | | explained_variance | 0.968 | | learning_rate | 0.000241 | | loss | -0.0199 | | n_updates | 1724 | | policy_gradient_loss | -0.0188 | | value_loss | 0.000334 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 54.1 | | ep_rew_mean | 0.831 | | time/ | | | fps | 1124 | | iterations | 433 | | time_elapsed | 3154 | | total_timesteps | 3547136 | | train/ | | | approx_kl | 0.058395542 | | clip_fraction | 0.348 | | clip_range | 0.146 | | entropy_loss | -4.7 | | explained_variance | 0.928 | | learning_rate | 0.000241 | | loss | -0.0186 | | n_updates | 1728 | | policy_gradient_loss | -0.0136 | | value_loss | 0.000704 | ----------------------------------------- --------------------------------------- | rollout/ | | | ep_len_mean | 48.6 | | ep_rew_mean | 0.849 | | time/ | | | fps | 1124 | | iterations | 434 | | time_elapsed | 3161 | | total_timesteps | 3555328 | | train/ | | | approx_kl | 0.0730995 | | clip_fraction | 0.374 | | clip_range | 0.146 | | entropy_loss | -4.79 | | explained_variance | 0.893 | | learning_rate | 0.000241 | | loss | -0.0381 | | n_updates | 1732 | | policy_gradient_loss | -0.0203 | | value_loss | 0.00119 | --------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 53.1 | | ep_rew_mean | 0.841 | | time/ | | | fps | 1124 | | iterations | 435 | | time_elapsed | 3168 | | total_timesteps | 3563520 | | train/ | | | approx_kl | 0.07831407 | | clip_fraction | 0.317 | | clip_range | 0.146 | | entropy_loss | -4.6 | | explained_variance | 0.932 | | learning_rate | 0.000241 | | loss | -0.026 | | n_updates | 1736 | | policy_gradient_loss | -0.0169 | | value_loss | 0.000522 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 46.3 | | ep_rew_mean | 0.853 | | time/ | | | fps | 1124 | | iterations | 436 | | time_elapsed | 3175 | | total_timesteps | 3571712 | | train/ | | | approx_kl | 0.09369155 | | clip_fraction | 0.359 | | clip_range | 0.146 | | entropy_loss | -4.7 | | explained_variance | 0.945 | | learning_rate | 0.000241 | | loss | -0.0339 | | n_updates | 1740 | | policy_gradient_loss | -0.0236 | | value_loss | 0.000592 | ---------------------------------------- --------------------------------------- | rollout/ | | | ep_len_mean | 48.5 | | ep_rew_mean | 0.85 | | time/ | | | fps | 1124 | | iterations | 437 | | time_elapsed | 3182 | | total_timesteps | 3579904 | | train/ | | | approx_kl | 0.0758425 | | clip_fraction | 0.31 | | clip_range | 0.146 | | entropy_loss | -4.48 | | explained_variance | 0.957 | | learning_rate | 0.000241 | | loss | -0.0106 | | n_updates | 1744 | | policy_gradient_loss | -0.00774 | | value_loss | 0.000277 | --------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 47.8 | | ep_rew_mean | 0.85 | | time/ | | | fps | 1124 | | iterations | 438 | | time_elapsed | 3189 | | total_timesteps | 3588096 | | train/ | | | approx_kl | 0.061206106 | | clip_fraction | 0.33 | | clip_range | 0.146 | | entropy_loss | -4.57 | | explained_variance | 0.94 | | learning_rate | 0.000241 | | loss | -0.0195 | | n_updates | 1748 | | policy_gradient_loss | -0.0141 | | value_loss | 0.000463 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 51.6 | | ep_rew_mean | 0.84 | | time/ | | | fps | 1125 | | iterations | 439 | | time_elapsed | 3196 | | total_timesteps | 3596288 | | train/ | | | approx_kl | 0.08174087 | | clip_fraction | 0.332 | | clip_range | 0.146 | | entropy_loss | -4.66 | | explained_variance | 0.949 | | learning_rate | 0.000241 | | loss | -0.0251 | | n_updates | 1752 | | policy_gradient_loss | -0.0175 | | value_loss | 0.000426 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 47.9 | | ep_rew_mean | 0.84 | | time/ | | | fps | 1125 | | iterations | 440 | | time_elapsed | 3203 | | total_timesteps | 3604480 | | train/ | | | approx_kl | 0.06932084 | | clip_fraction | 0.383 | | clip_range | 0.146 | | entropy_loss | -4.72 | | explained_variance | 0.948 | | learning_rate | 0.000241 | | loss | -0.0366 | | n_updates | 1756 | | policy_gradient_loss | -0.0229 | | value_loss | 0.000586 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 47.5 | | ep_rew_mean | 0.846 | | time/ | | | fps | 1125 | | iterations | 441 | | time_elapsed | 3210 | | total_timesteps | 3612672 | | train/ | | | approx_kl | 0.054611113 | | clip_fraction | 0.285 | | clip_range | 0.145 | | entropy_loss | -4.65 | | explained_variance | 0.952 | | learning_rate | 0.000241 | | loss | -0.025 | | n_updates | 1760 | | policy_gradient_loss | -0.0176 | | value_loss | 0.000384 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 56.1 | | ep_rew_mean | 0.827 | | time/ | | | fps | 1125 | | iterations | 442 | | time_elapsed | 3217 | | total_timesteps | 3620864 | | train/ | | | approx_kl | 0.044505477 | | clip_fraction | 0.319 | | clip_range | 0.145 | | entropy_loss | -4.62 | | explained_variance | 0.952 | | learning_rate | 0.000241 | | loss | -0.0149 | | n_updates | 1764 | | policy_gradient_loss | -0.0141 | | value_loss | 0.000389 | ----------------------------------------- --------------------------------------- | rollout/ | | | ep_len_mean | 51.8 | | ep_rew_mean | 0.83 | | time/ | | | fps | 1125 | | iterations | 443 | | time_elapsed | 3224 | | total_timesteps | 3629056 | | train/ | | | approx_kl | 0.0603766 | | clip_fraction | 0.358 | | clip_range | 0.145 | | entropy_loss | -4.96 | | explained_variance | 0.963 | | learning_rate | 0.000241 | | loss | -0.0379 | | n_updates | 1768 | | policy_gradient_loss | -0.0251 | | value_loss | 0.000506 | --------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 46.7 | | ep_rew_mean | 0.844 | | time/ | | | fps | 1125 | | iterations | 444 | | time_elapsed | 3231 | | total_timesteps | 3637248 | | train/ | | | approx_kl | 0.10381849 | | clip_fraction | 0.346 | | clip_range | 0.145 | | entropy_loss | -4.69 | | explained_variance | 0.951 | | learning_rate | 0.000241 | | loss | -0.0195 | | n_updates | 1772 | | policy_gradient_loss | -0.019 | | value_loss | 0.000497 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 54.9 | | ep_rew_mean | 0.83 | | time/ | | | fps | 1125 | | iterations | 445 | | time_elapsed | 3238 | | total_timesteps | 3645440 | | train/ | | | approx_kl | 0.037427682 | | clip_fraction | 0.27 | | clip_range | 0.145 | | entropy_loss | -4.46 | | explained_variance | 0.975 | | learning_rate | 0.000241 | | loss | -0.00952 | | n_updates | 1776 | | policy_gradient_loss | -0.00871 | | value_loss | 0.000168 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 57.9 | | ep_rew_mean | 0.823 | | time/ | | | fps | 1125 | | iterations | 446 | | time_elapsed | 3245 | | total_timesteps | 3653632 | | train/ | | | approx_kl | 0.07988455 | | clip_fraction | 0.339 | | clip_range | 0.145 | | entropy_loss | -4.71 | | explained_variance | 0.942 | | learning_rate | 0.000241 | | loss | -0.0377 | | n_updates | 1780 | | policy_gradient_loss | -0.021 | | value_loss | 0.000606 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 47.6 | | ep_rew_mean | 0.842 | | time/ | | | fps | 1125 | | iterations | 447 | | time_elapsed | 3253 | | total_timesteps | 3661824 | | train/ | | | approx_kl | 0.09466633 | | clip_fraction | 0.368 | | clip_range | 0.145 | | entropy_loss | -4.86 | | explained_variance | 0.945 | | learning_rate | 0.000241 | | loss | -0.0314 | | n_updates | 1784 | | policy_gradient_loss | -0.023 | | value_loss | 0.000706 | ---------------------------------------- --------------------------------------- | rollout/ | | | ep_len_mean | 54.8 | | ep_rew_mean | 0.819 | | time/ | | | fps | 1125 | | iterations | 448 | | time_elapsed | 3260 | | total_timesteps | 3670016 | | train/ | | | approx_kl | 0.0637682 | | clip_fraction | 0.339 | | clip_range | 0.145 | | entropy_loss | -4.56 | | explained_variance | 0.93 | | learning_rate | 0.000241 | | loss | -0.0144 | | n_updates | 1788 | | policy_gradient_loss | -0.0141 | | value_loss | 0.000567 | --------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 49.9 | | ep_rew_mean | 0.836 | | time/ | | | fps | 1125 | | iterations | 449 | | time_elapsed | 3267 | | total_timesteps | 3678208 | | train/ | | | approx_kl | 0.09321886 | | clip_fraction | 0.373 | | clip_range | 0.145 | | entropy_loss | -4.9 | | explained_variance | 0.926 | | learning_rate | 0.000241 | | loss | -0.0284 | | n_updates | 1792 | | policy_gradient_loss | -0.0225 | | value_loss | 0.00075 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 55.3 | | ep_rew_mean | 0.829 | | time/ | | | fps | 1125 | | iterations | 450 | | time_elapsed | 3274 | | total_timesteps | 3686400 | | train/ | | | approx_kl | 0.059952352 | | clip_fraction | 0.285 | | clip_range | 0.145 | | entropy_loss | -4.74 | | explained_variance | 0.961 | | learning_rate | 0.000241 | | loss | -0.0196 | | n_updates | 1796 | | policy_gradient_loss | -0.0194 | | value_loss | 0.000358 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 49.6 | | ep_rew_mean | 0.844 | | time/ | | | fps | 1126 | | iterations | 451 | | time_elapsed | 3281 | | total_timesteps | 3694592 | | train/ | | | approx_kl | 0.07412451 | | clip_fraction | 0.346 | | clip_range | 0.145 | | entropy_loss | -5.05 | | explained_variance | 0.954 | | learning_rate | 0.000241 | | loss | -0.0285 | | n_updates | 1800 | | policy_gradient_loss | -0.0251 | | value_loss | 0.000586 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 50.1 | | ep_rew_mean | 0.842 | | time/ | | | fps | 1126 | | iterations | 452 | | time_elapsed | 3288 | | total_timesteps | 3702784 | | train/ | | | approx_kl | 0.07055646 | | clip_fraction | 0.334 | | clip_range | 0.145 | | entropy_loss | -4.82 | | explained_variance | 0.935 | | learning_rate | 0.000241 | | loss | -0.0315 | | n_updates | 1804 | | policy_gradient_loss | -0.018 | | value_loss | 0.00061 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 52.7 | | ep_rew_mean | 0.84 | | time/ | | | fps | 1126 | | iterations | 453 | | time_elapsed | 3295 | | total_timesteps | 3710976 | | train/ | | | approx_kl | 0.08173225 | | clip_fraction | 0.341 | | clip_range | 0.145 | | entropy_loss | -4.89 | | explained_variance | 0.944 | | learning_rate | 0.000241 | | loss | -0.0325 | | n_updates | 1808 | | policy_gradient_loss | -0.0224 | | value_loss | 0.000659 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 50 | | ep_rew_mean | 0.842 | | time/ | | | fps | 1126 | | iterations | 454 | | time_elapsed | 3302 | | total_timesteps | 3719168 | | train/ | | | approx_kl | 0.07032408 | | clip_fraction | 0.321 | | clip_range | 0.145 | | entropy_loss | -4.84 | | explained_variance | 0.953 | | learning_rate | 0.000241 | | loss | -0.0288 | | n_updates | 1812 | | policy_gradient_loss | -0.0192 | | value_loss | 0.000501 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 53 | | ep_rew_mean | 0.836 | | time/ | | | fps | 1126 | | iterations | 455 | | time_elapsed | 3309 | | total_timesteps | 3727360 | | train/ | | | approx_kl | 0.07507625 | | clip_fraction | 0.359 | | clip_range | 0.145 | | entropy_loss | -4.7 | | explained_variance | 0.941 | | learning_rate | 0.000241 | | loss | -0.0205 | | n_updates | 1816 | | policy_gradient_loss | -0.0168 | | value_loss | 0.000622 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 50.8 | | ep_rew_mean | 0.843 | | time/ | | | fps | 1126 | | iterations | 456 | | time_elapsed | 3316 | | total_timesteps | 3735552 | | train/ | | | approx_kl | 0.08481913 | | clip_fraction | 0.314 | | clip_range | 0.145 | | entropy_loss | -4.78 | | explained_variance | 0.947 | | learning_rate | 0.000241 | | loss | -0.0193 | | n_updates | 1820 | | policy_gradient_loss | -0.0235 | | value_loss | 0.000559 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 55.8 | | ep_rew_mean | 0.824 | | time/ | | | fps | 1126 | | iterations | 457 | | time_elapsed | 3323 | | total_timesteps | 3743744 | | train/ | | | approx_kl | 0.06894081 | | clip_fraction | 0.291 | | clip_range | 0.145 | | entropy_loss | -4.68 | | explained_variance | 0.968 | | learning_rate | 0.000241 | | loss | -0.0329 | | n_updates | 1824 | | policy_gradient_loss | -0.0185 | | value_loss | 0.000268 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 52.2 | | ep_rew_mean | 0.84 | | time/ | | | fps | 1126 | | iterations | 458 | | time_elapsed | 3330 | | total_timesteps | 3751936 | | train/ | | | approx_kl | 0.07439946 | | clip_fraction | 0.366 | | clip_range | 0.145 | | entropy_loss | -4.88 | | explained_variance | 0.943 | | learning_rate | 0.000241 | | loss | -0.0386 | | n_updates | 1828 | | policy_gradient_loss | -0.0238 | | value_loss | 0.000681 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 57.7 | | ep_rew_mean | 0.826 | | time/ | | | fps | 1126 | | iterations | 459 | | time_elapsed | 3337 | | total_timesteps | 3760128 | | train/ | | | approx_kl | 0.065483175 | | clip_fraction | 0.349 | | clip_range | 0.145 | | entropy_loss | -4.76 | | explained_variance | 0.939 | | learning_rate | 0.000241 | | loss | -0.0253 | | n_updates | 1832 | | policy_gradient_loss | -0.0186 | | value_loss | 0.000664 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 46.7 | | ep_rew_mean | 0.852 | | time/ | | | fps | 1126 | | iterations | 460 | | time_elapsed | 3344 | | total_timesteps | 3768320 | | train/ | | | approx_kl | 0.08090966 | | clip_fraction | 0.345 | | clip_range | 0.145 | | entropy_loss | -4.97 | | explained_variance | 0.93 | | learning_rate | 0.000241 | | loss | -0.0284 | | n_updates | 1836 | | policy_gradient_loss | -0.0233 | | value_loss | 0.000845 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 50.7 | | ep_rew_mean | 0.846 | | time/ | | | fps | 1126 | | iterations | 461 | | time_elapsed | 3352 | | total_timesteps | 3776512 | | train/ | | | approx_kl | 0.04875502 | | clip_fraction | 0.294 | | clip_range | 0.145 | | entropy_loss | -4.69 | | explained_variance | 0.944 | | learning_rate | 0.000241 | | loss | -0.0188 | | n_updates | 1840 | | policy_gradient_loss | -0.0118 | | value_loss | 0.00041 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 51.1 | | ep_rew_mean | 0.843 | | time/ | | | fps | 1126 | | iterations | 462 | | time_elapsed | 3359 | | total_timesteps | 3784704 | | train/ | | | approx_kl | 0.052373186 | | clip_fraction | 0.321 | | clip_range | 0.145 | | entropy_loss | -4.79 | | explained_variance | 0.944 | | learning_rate | 0.000241 | | loss | -0.0235 | | n_updates | 1844 | | policy_gradient_loss | -0.0157 | | value_loss | 0.000497 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 52.2 | | ep_rew_mean | 0.839 | | time/ | | | fps | 1126 | | iterations | 463 | | time_elapsed | 3366 | | total_timesteps | 3792896 | | train/ | | | approx_kl | 0.057323508 | | clip_fraction | 0.331 | | clip_range | 0.145 | | entropy_loss | -4.94 | | explained_variance | 0.917 | | learning_rate | 0.000241 | | loss | -0.0234 | | n_updates | 1848 | | policy_gradient_loss | -0.0187 | | value_loss | 0.000796 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 54.2 | | ep_rew_mean | 0.839 | | time/ | | | fps | 1126 | | iterations | 464 | | time_elapsed | 3373 | | total_timesteps | 3801088 | | train/ | | | approx_kl | 0.05739809 | | clip_fraction | 0.324 | | clip_range | 0.145 | | entropy_loss | -5.02 | | explained_variance | 0.941 | | learning_rate | 0.000241 | | loss | -0.0263 | | n_updates | 1852 | | policy_gradient_loss | -0.0235 | | value_loss | 0.000609 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 48.5 | | ep_rew_mean | 0.849 | | time/ | | | fps | 1126 | | iterations | 465 | | time_elapsed | 3380 | | total_timesteps | 3809280 | | train/ | | | approx_kl | 0.05994657 | | clip_fraction | 0.37 | | clip_range | 0.145 | | entropy_loss | -5.07 | | explained_variance | 0.902 | | learning_rate | 0.000241 | | loss | -0.0342 | | n_updates | 1856 | | policy_gradient_loss | -0.0229 | | value_loss | 0.00122 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 53 | | ep_rew_mean | 0.838 | | time/ | | | fps | 1127 | | iterations | 466 | | time_elapsed | 3387 | | total_timesteps | 3817472 | | train/ | | | approx_kl | 0.055929467 | | clip_fraction | 0.303 | | clip_range | 0.145 | | entropy_loss | -4.94 | | explained_variance | 0.962 | | learning_rate | 0.000241 | | loss | -0.0331 | | n_updates | 1860 | | policy_gradient_loss | -0.0196 | | value_loss | 0.000404 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 60.8 | | ep_rew_mean | 0.81 | | time/ | | | fps | 1127 | | iterations | 467 | | time_elapsed | 3394 | | total_timesteps | 3825664 | | train/ | | | approx_kl | 0.084799156 | | clip_fraction | 0.367 | | clip_range | 0.145 | | entropy_loss | -5.03 | | explained_variance | 0.938 | | learning_rate | 0.000241 | | loss | -0.0271 | | n_updates | 1864 | | policy_gradient_loss | -0.0214 | | value_loss | 0.000748 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 51.1 | | ep_rew_mean | 0.839 | | time/ | | | fps | 1127 | | iterations | 468 | | time_elapsed | 3401 | | total_timesteps | 3833856 | | train/ | | | approx_kl | 0.064770915 | | clip_fraction | 0.385 | | clip_range | 0.145 | | entropy_loss | -5.15 | | explained_variance | 0.94 | | learning_rate | 0.000241 | | loss | -0.0321 | | n_updates | 1868 | | policy_gradient_loss | -0.0254 | | value_loss | 0.000789 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 55.1 | | ep_rew_mean | 0.826 | | time/ | | | fps | 1127 | | iterations | 469 | | time_elapsed | 3408 | | total_timesteps | 3842048 | | train/ | | | approx_kl | 0.04445334 | | clip_fraction | 0.304 | | clip_range | 0.145 | | entropy_loss | -4.87 | | explained_variance | 0.944 | | learning_rate | 0.000241 | | loss | -0.0282 | | n_updates | 1872 | | policy_gradient_loss | -0.0162 | | value_loss | 0.000471 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 53.1 | | ep_rew_mean | 0.834 | | time/ | | | fps | 1127 | | iterations | 470 | | time_elapsed | 3415 | | total_timesteps | 3850240 | | train/ | | | approx_kl | 0.07493868 | | clip_fraction | 0.385 | | clip_range | 0.145 | | entropy_loss | -5.01 | | explained_variance | 0.948 | | learning_rate | 0.00024 | | loss | -0.0342 | | n_updates | 1876 | | policy_gradient_loss | -0.0248 | | value_loss | 0.000677 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 49.6 | | ep_rew_mean | 0.845 | | time/ | | | fps | 1127 | | iterations | 471 | | time_elapsed | 3422 | | total_timesteps | 3858432 | | train/ | | | approx_kl | 0.079786524 | | clip_fraction | 0.387 | | clip_range | 0.145 | | entropy_loss | -4.96 | | explained_variance | 0.952 | | learning_rate | 0.00024 | | loss | -0.0387 | | n_updates | 1880 | | policy_gradient_loss | -0.0232 | | value_loss | 0.000661 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 52.3 | | ep_rew_mean | 0.838 | | time/ | | | fps | 1127 | | iterations | 472 | | time_elapsed | 3429 | | total_timesteps | 3866624 | | train/ | | | approx_kl | 0.057607003 | | clip_fraction | 0.342 | | clip_range | 0.145 | | entropy_loss | -4.68 | | explained_variance | 0.948 | | learning_rate | 0.00024 | | loss | -0.0237 | | n_updates | 1884 | | policy_gradient_loss | -0.0144 | | value_loss | 0.000466 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 52 | | ep_rew_mean | 0.834 | | time/ | | | fps | 1127 | | iterations | 473 | | time_elapsed | 3436 | | total_timesteps | 3874816 | | train/ | | | approx_kl | 0.07106587 | | clip_fraction | 0.323 | | clip_range | 0.145 | | entropy_loss | -4.8 | | explained_variance | 0.947 | | learning_rate | 0.00024 | | loss | -0.0304 | | n_updates | 1888 | | policy_gradient_loss | -0.0188 | | value_loss | 0.000559 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 53.7 | | ep_rew_mean | 0.829 | | time/ | | | fps | 1127 | | iterations | 474 | | time_elapsed | 3443 | | total_timesteps | 3883008 | | train/ | | | approx_kl | 0.060432144 | | clip_fraction | 0.32 | | clip_range | 0.145 | | entropy_loss | -4.75 | | explained_variance | 0.944 | | learning_rate | 0.00024 | | loss | -0.023 | | n_updates | 1892 | | policy_gradient_loss | -0.0149 | | value_loss | 0.000553 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 48.2 | | ep_rew_mean | 0.846 | | time/ | | | fps | 1127 | | iterations | 475 | | time_elapsed | 3450 | | total_timesteps | 3891200 | | train/ | | | approx_kl | 0.07106549 | | clip_fraction | 0.38 | | clip_range | 0.145 | | entropy_loss | -4.81 | | explained_variance | 0.949 | | learning_rate | 0.00024 | | loss | -0.0219 | | n_updates | 1896 | | policy_gradient_loss | -0.0183 | | value_loss | 0.000579 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 50.9 | | ep_rew_mean | 0.841 | | time/ | | | fps | 1127 | | iterations | 476 | | time_elapsed | 3457 | | total_timesteps | 3899392 | | train/ | | | approx_kl | 0.07195568 | | clip_fraction | 0.293 | | clip_range | 0.145 | | entropy_loss | -4.78 | | explained_variance | 0.958 | | learning_rate | 0.00024 | | loss | -0.0305 | | n_updates | 1900 | | policy_gradient_loss | -0.0186 | | value_loss | 0.00039 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 50.3 | | ep_rew_mean | 0.843 | | time/ | | | fps | 1127 | | iterations | 477 | | time_elapsed | 3465 | | total_timesteps | 3907584 | | train/ | | | approx_kl | 0.091775574 | | clip_fraction | 0.362 | | clip_range | 0.145 | | entropy_loss | -4.94 | | explained_variance | 0.963 | | learning_rate | 0.00024 | | loss | -0.0264 | | n_updates | 1904 | | policy_gradient_loss | -0.0239 | | value_loss | 0.000425 | ----------------------------------------- --------------------------------------- | rollout/ | | | ep_len_mean | 46.7 | | ep_rew_mean | 0.852 | | time/ | | | fps | 1127 | | iterations | 478 | | time_elapsed | 3472 | | total_timesteps | 3915776 | | train/ | | | approx_kl | 0.0892612 | | clip_fraction | 0.362 | | clip_range | 0.145 | | entropy_loss | -4.85 | | explained_variance | 0.953 | | learning_rate | 0.00024 | | loss | -0.0272 | | n_updates | 1908 | | policy_gradient_loss | -0.0191 | | value_loss | 0.000489 | --------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 49.2 | | ep_rew_mean | 0.845 | | time/ | | | fps | 1127 | | iterations | 479 | | time_elapsed | 3479 | | total_timesteps | 3923968 | | train/ | | | approx_kl | 0.062186938 | | clip_fraction | 0.333 | | clip_range | 0.145 | | entropy_loss | -4.78 | | explained_variance | 0.959 | | learning_rate | 0.00024 | | loss | -0.0251 | | n_updates | 1912 | | policy_gradient_loss | -0.0177 | | value_loss | 0.000383 | ----------------------------------------- --------------------------------------- | rollout/ | | | ep_len_mean | 53.8 | | ep_rew_mean | 0.839 | | time/ | | | fps | 1127 | | iterations | 480 | | time_elapsed | 3486 | | total_timesteps | 3932160 | | train/ | | | approx_kl | 0.0640039 | | clip_fraction | 0.325 | | clip_range | 0.145 | | entropy_loss | -4.82 | | explained_variance | 0.965 | | learning_rate | 0.00024 | | loss | -0.0262 | | n_updates | 1916 | | policy_gradient_loss | -0.0193 | | value_loss | 0.000369 | --------------------------------------- --------------------------------------- | rollout/ | | | ep_len_mean | 51 | | ep_rew_mean | 0.844 | | time/ | | | fps | 1127 | | iterations | 481 | | time_elapsed | 3493 | | total_timesteps | 3940352 | | train/ | | | approx_kl | 0.0921659 | | clip_fraction | 0.319 | | clip_range | 0.145 | | entropy_loss | -4.89 | | explained_variance | 0.971 | | learning_rate | 0.00024 | | loss | -0.0288 | | n_updates | 1920 | | policy_gradient_loss | -0.0201 | | value_loss | 0.000325 | --------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 53.5 | | ep_rew_mean | 0.833 | | time/ | | | fps | 1127 | | iterations | 482 | | time_elapsed | 3500 | | total_timesteps | 3948544 | | train/ | | | approx_kl | 0.07869721 | | clip_fraction | 0.314 | | clip_range | 0.145 | | entropy_loss | -4.74 | | explained_variance | 0.965 | | learning_rate | 0.00024 | | loss | -0.0233 | | n_updates | 1924 | | policy_gradient_loss | -0.0143 | | value_loss | 0.000311 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 58.3 | | ep_rew_mean | 0.826 | | time/ | | | fps | 1128 | | iterations | 483 | | time_elapsed | 3507 | | total_timesteps | 3956736 | | train/ | | | approx_kl | 0.07095386 | | clip_fraction | 0.351 | | clip_range | 0.145 | | entropy_loss | -4.83 | | explained_variance | 0.943 | | learning_rate | 0.00024 | | loss | -0.0231 | | n_updates | 1928 | | policy_gradient_loss | -0.0218 | | value_loss | 0.000599 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 51 | | ep_rew_mean | 0.843 | | time/ | | | fps | 1128 | | iterations | 484 | | time_elapsed | 3514 | | total_timesteps | 3964928 | | train/ | | | approx_kl | 0.06842169 | | clip_fraction | 0.378 | | clip_range | 0.145 | | entropy_loss | -5.03 | | explained_variance | 0.946 | | learning_rate | 0.00024 | | loss | -0.0364 | | n_updates | 1932 | | policy_gradient_loss | -0.0258 | | value_loss | 0.000743 | ---------------------------------------- --------------------------------------- | rollout/ | | | ep_len_mean | 48.6 | | ep_rew_mean | 0.843 | | time/ | | | fps | 1128 | | iterations | 485 | | time_elapsed | 3521 | | total_timesteps | 3973120 | | train/ | | | approx_kl | 0.0649405 | | clip_fraction | 0.322 | | clip_range | 0.145 | | entropy_loss | -4.87 | | explained_variance | 0.958 | | learning_rate | 0.00024 | | loss | -0.0158 | | n_updates | 1936 | | policy_gradient_loss | -0.0199 | | value_loss | 0.000449 | --------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 47 | | ep_rew_mean | 0.848 | | time/ | | | fps | 1128 | | iterations | 486 | | time_elapsed | 3528 | | total_timesteps | 3981312 | | train/ | | | approx_kl | 0.06282572 | | clip_fraction | 0.323 | | clip_range | 0.145 | | entropy_loss | -4.71 | | explained_variance | 0.967 | | learning_rate | 0.00024 | | loss | -0.0195 | | n_updates | 1940 | | policy_gradient_loss | -0.0141 | | value_loss | 0.000281 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 53.4 | | ep_rew_mean | 0.825 | | time/ | | | fps | 1128 | | iterations | 487 | | time_elapsed | 3535 | | total_timesteps | 3989504 | | train/ | | | approx_kl | 0.044741083 | | clip_fraction | 0.24 | | clip_range | 0.145 | | entropy_loss | -4.66 | | explained_variance | 0.975 | | learning_rate | 0.00024 | | loss | -0.0046 | | n_updates | 1944 | | policy_gradient_loss | -0.00936 | | value_loss | 0.000165 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 52.3 | | ep_rew_mean | 0.84 | | time/ | | | fps | 1128 | | iterations | 488 | | time_elapsed | 3542 | | total_timesteps | 3997696 | | train/ | | | approx_kl | 0.05923363 | | clip_fraction | 0.325 | | clip_range | 0.145 | | entropy_loss | -4.85 | | explained_variance | 0.966 | | learning_rate | 0.00024 | | loss | -0.0225 | | n_updates | 1948 | | policy_gradient_loss | -0.0188 | | value_loss | 0.000367 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 54.2 | | ep_rew_mean | 0.838 | | time/ | | | fps | 1128 | | iterations | 489 | | time_elapsed | 3550 | | total_timesteps | 4005888 | | train/ | | | approx_kl | 0.061747868 | | clip_fraction | 0.372 | | clip_range | 0.145 | | entropy_loss | -4.86 | | explained_variance | 0.948 | | learning_rate | 0.00024 | | loss | -0.0191 | | n_updates | 1952 | | policy_gradient_loss | -0.0161 | | value_loss | 0.00053 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 48.5 | | ep_rew_mean | 0.85 | | time/ | | | fps | 1128 | | iterations | 490 | | time_elapsed | 3557 | | total_timesteps | 4014080 | | train/ | | | approx_kl | 0.07030307 | | clip_fraction | 0.339 | | clip_range | 0.145 | | entropy_loss | -5.03 | | explained_variance | 0.952 | | learning_rate | 0.00024 | | loss | -0.0367 | | n_updates | 1956 | | policy_gradient_loss | -0.0244 | | value_loss | 0.000581 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 48.8 | | ep_rew_mean | 0.851 | | time/ | | | fps | 1128 | | iterations | 491 | | time_elapsed | 3564 | | total_timesteps | 4022272 | | train/ | | | approx_kl | 0.073139966 | | clip_fraction | 0.289 | | clip_range | 0.145 | | entropy_loss | -4.83 | | explained_variance | 0.934 | | learning_rate | 0.00024 | | loss | -0.0222 | | n_updates | 1960 | | policy_gradient_loss | -0.0153 | | value_loss | 0.000522 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 50.4 | | ep_rew_mean | 0.839 | | time/ | | | fps | 1128 | | iterations | 492 | | time_elapsed | 3572 | | total_timesteps | 4030464 | | train/ | | | approx_kl | 0.060530405 | | clip_fraction | 0.289 | | clip_range | 0.145 | | entropy_loss | -4.8 | | explained_variance | 0.941 | | learning_rate | 0.00024 | | loss | -0.0179 | | n_updates | 1964 | | policy_gradient_loss | -0.0137 | | value_loss | 0.000439 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 49.2 | | ep_rew_mean | 0.849 | | time/ | | | fps | 1128 | | iterations | 493 | | time_elapsed | 3579 | | total_timesteps | 4038656 | | train/ | | | approx_kl | 0.05481425 | | clip_fraction | 0.332 | | clip_range | 0.145 | | entropy_loss | -4.93 | | explained_variance | 0.948 | | learning_rate | 0.00024 | | loss | -0.0315 | | n_updates | 1968 | | policy_gradient_loss | -0.0185 | | value_loss | 0.000513 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 55.8 | | ep_rew_mean | 0.83 | | time/ | | | fps | 1128 | | iterations | 494 | | time_elapsed | 3586 | | total_timesteps | 4046848 | | train/ | | | approx_kl | 0.06432268 | | clip_fraction | 0.283 | | clip_range | 0.145 | | entropy_loss | -4.94 | | explained_variance | 0.949 | | learning_rate | 0.00024 | | loss | -0.0193 | | n_updates | 1972 | | policy_gradient_loss | -0.0155 | | value_loss | 0.000409 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 52.7 | | ep_rew_mean | 0.84 | | time/ | | | fps | 1128 | | iterations | 495 | | time_elapsed | 3594 | | total_timesteps | 4055040 | | train/ | | | approx_kl | 0.068503655 | | clip_fraction | 0.34 | | clip_range | 0.145 | | entropy_loss | -5.18 | | explained_variance | 0.896 | | learning_rate | 0.00024 | | loss | -0.0287 | | n_updates | 1976 | | policy_gradient_loss | -0.0233 | | value_loss | 0.00123 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 46 | | ep_rew_mean | 0.853 | | time/ | | | fps | 1128 | | iterations | 496 | | time_elapsed | 3601 | | total_timesteps | 4063232 | | train/ | | | approx_kl | 0.05970429 | | clip_fraction | 0.333 | | clip_range | 0.145 | | entropy_loss | -4.96 | | explained_variance | 0.952 | | learning_rate | 0.00024 | | loss | -0.0324 | | n_updates | 1980 | | policy_gradient_loss | -0.0197 | | value_loss | 0.000424 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 55.5 | | ep_rew_mean | 0.834 | | time/ | | | fps | 1128 | | iterations | 497 | | time_elapsed | 3608 | | total_timesteps | 4071424 | | train/ | | | approx_kl | 0.04966297 | | clip_fraction | 0.226 | | clip_range | 0.145 | | entropy_loss | -4.83 | | explained_variance | 0.987 | | learning_rate | 0.00024 | | loss | -0.00716 | | n_updates | 1984 | | policy_gradient_loss | -0.0101 | | value_loss | 9.61e-05 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 56.8 | | ep_rew_mean | 0.832 | | time/ | | | fps | 1128 | | iterations | 498 | | time_elapsed | 3615 | | total_timesteps | 4079616 | | train/ | | | approx_kl | 0.06246019 | | clip_fraction | 0.329 | | clip_range | 0.145 | | entropy_loss | -5.15 | | explained_variance | 0.918 | | learning_rate | 0.00024 | | loss | -0.0242 | | n_updates | 1988 | | policy_gradient_loss | -0.0206 | | value_loss | 0.000912 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 49.9 | | ep_rew_mean | 0.84 | | time/ | | | fps | 1128 | | iterations | 499 | | time_elapsed | 3623 | | total_timesteps | 4087808 | | train/ | | | approx_kl | 0.056641333 | | clip_fraction | 0.298 | | clip_range | 0.145 | | entropy_loss | -5.21 | | explained_variance | 0.909 | | learning_rate | 0.00024 | | loss | -0.0199 | | n_updates | 1992 | | policy_gradient_loss | -0.0189 | | value_loss | 0.00105 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 52.1 | | ep_rew_mean | 0.836 | | time/ | | | fps | 1128 | | iterations | 500 | | time_elapsed | 3630 | | total_timesteps | 4096000 | | train/ | | | approx_kl | 0.08830541 | | clip_fraction | 0.301 | | clip_range | 0.145 | | entropy_loss | -5.03 | | explained_variance | 0.899 | | learning_rate | 0.00024 | | loss | -0.0141 | | n_updates | 1996 | | policy_gradient_loss | -0.0149 | | value_loss | 0.000865 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 56.4 | | ep_rew_mean | 0.828 | | time/ | | | fps | 1128 | | iterations | 501 | | time_elapsed | 3638 | | total_timesteps | 4104192 | | train/ | | | approx_kl | 0.062667474 | | clip_fraction | 0.335 | | clip_range | 0.145 | | entropy_loss | -5.23 | | explained_variance | 0.924 | | learning_rate | 0.00024 | | loss | -0.0272 | | n_updates | 2000 | | policy_gradient_loss | -0.0226 | | value_loss | 0.000793 | ----------------------------------------- --------------------------------------- | rollout/ | | | ep_len_mean | 60.3 | | ep_rew_mean | 0.824 | | time/ | | | fps | 1128 | | iterations | 502 | | time_elapsed | 3645 | | total_timesteps | 4112384 | | train/ | | | approx_kl | 0.0732182 | | clip_fraction | 0.366 | | clip_range | 0.145 | | entropy_loss | -5.4 | | explained_variance | 0.938 | | learning_rate | 0.00024 | | loss | -0.0311 | | n_updates | 2004 | | policy_gradient_loss | -0.0268 | | value_loss | 0.000823 | --------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 50.9 | | ep_rew_mean | 0.84 | | time/ | | | fps | 1128 | | iterations | 503 | | time_elapsed | 3652 | | total_timesteps | 4120576 | | train/ | | | approx_kl | 0.06136915 | | clip_fraction | 0.367 | | clip_range | 0.145 | | entropy_loss | -5.43 | | explained_variance | 0.935 | | learning_rate | 0.00024 | | loss | -0.0337 | | n_updates | 2008 | | policy_gradient_loss | -0.0272 | | value_loss | 0.000903 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 55 | | ep_rew_mean | 0.831 | | time/ | | | fps | 1128 | | iterations | 504 | | time_elapsed | 3659 | | total_timesteps | 4128768 | | train/ | | | approx_kl | 0.059064634 | | clip_fraction | 0.328 | | clip_range | 0.145 | | entropy_loss | -5.21 | | explained_variance | 0.949 | | learning_rate | 0.00024 | | loss | -0.0228 | | n_updates | 2012 | | policy_gradient_loss | -0.0209 | | value_loss | 0.000578 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 51.3 | | ep_rew_mean | 0.844 | | time/ | | | fps | 1128 | | iterations | 505 | | time_elapsed | 3666 | | total_timesteps | 4136960 | | train/ | | | approx_kl | 0.055064663 | | clip_fraction | 0.364 | | clip_range | 0.145 | | entropy_loss | -5.44 | | explained_variance | 0.932 | | learning_rate | 0.00024 | | loss | -0.0399 | | n_updates | 2016 | | policy_gradient_loss | -0.0264 | | value_loss | 0.0009 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 56.2 | | ep_rew_mean | 0.819 | | time/ | | | fps | 1128 | | iterations | 506 | | time_elapsed | 3673 | | total_timesteps | 4145152 | | train/ | | | approx_kl | 0.04104404 | | clip_fraction | 0.268 | | clip_range | 0.145 | | entropy_loss | -5.24 | | explained_variance | 0.937 | | learning_rate | 0.00024 | | loss | -0.029 | | n_updates | 2020 | | policy_gradient_loss | -0.0197 | | value_loss | 0.000598 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 55.6 | | ep_rew_mean | 0.833 | | time/ | | | fps | 1128 | | iterations | 507 | | time_elapsed | 3681 | | total_timesteps | 4153344 | | train/ | | | approx_kl | 0.04690075 | | clip_fraction | 0.307 | | clip_range | 0.145 | | entropy_loss | -5.49 | | explained_variance | 0.947 | | learning_rate | 0.00024 | | loss | -0.0305 | | n_updates | 2024 | | policy_gradient_loss | -0.0251 | | value_loss | 0.000696 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 49.4 | | ep_rew_mean | 0.846 | | time/ | | | fps | 1128 | | iterations | 508 | | time_elapsed | 3688 | | total_timesteps | 4161536 | | train/ | | | approx_kl | 0.06569204 | | clip_fraction | 0.36 | | clip_range | 0.145 | | entropy_loss | -5.52 | | explained_variance | 0.915 | | learning_rate | 0.00024 | | loss | -0.0262 | | n_updates | 2028 | | policy_gradient_loss | -0.0226 | | value_loss | 0.00115 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 57.5 | | ep_rew_mean | 0.827 | | time/ | | | fps | 1128 | | iterations | 509 | | time_elapsed | 3695 | | total_timesteps | 4169728 | | train/ | | | approx_kl | 0.03677687 | | clip_fraction | 0.303 | | clip_range | 0.145 | | entropy_loss | -5.37 | | explained_variance | 0.916 | | learning_rate | 0.00024 | | loss | -0.0311 | | n_updates | 2032 | | policy_gradient_loss | -0.0179 | | value_loss | 0.000819 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 53.4 | | ep_rew_mean | 0.828 | | time/ | | | fps | 1128 | | iterations | 510 | | time_elapsed | 3703 | | total_timesteps | 4177920 | | train/ | | | approx_kl | 0.055058636 | | clip_fraction | 0.334 | | clip_range | 0.145 | | entropy_loss | -5.61 | | explained_variance | 0.931 | | learning_rate | 0.00024 | | loss | -0.039 | | n_updates | 2036 | | policy_gradient_loss | -0.026 | | value_loss | 0.000987 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 51.2 | | ep_rew_mean | 0.839 | | time/ | | | fps | 1128 | | iterations | 511 | | time_elapsed | 3710 | | total_timesteps | 4186112 | | train/ | | | approx_kl | 0.049495522 | | clip_fraction | 0.308 | | clip_range | 0.145 | | entropy_loss | -5.37 | | explained_variance | 0.948 | | learning_rate | 0.00024 | | loss | -0.0311 | | n_updates | 2040 | | policy_gradient_loss | -0.0225 | | value_loss | 0.000542 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 57.3 | | ep_rew_mean | 0.815 | | time/ | | | fps | 1128 | | iterations | 512 | | time_elapsed | 3717 | | total_timesteps | 4194304 | | train/ | | | approx_kl | 0.054122627 | | clip_fraction | 0.359 | | clip_range | 0.145 | | entropy_loss | -5.4 | | explained_variance | 0.948 | | learning_rate | 0.00024 | | loss | -0.0356 | | n_updates | 2044 | | policy_gradient_loss | -0.0219 | | value_loss | 0.000608 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 56.2 | | ep_rew_mean | 0.825 | | time/ | | | fps | 1128 | | iterations | 513 | | time_elapsed | 3724 | | total_timesteps | 4202496 | | train/ | | | approx_kl | 0.057738528 | | clip_fraction | 0.347 | | clip_range | 0.145 | | entropy_loss | -5.6 | | explained_variance | 0.936 | | learning_rate | 0.00024 | | loss | -0.034 | | n_updates | 2048 | | policy_gradient_loss | -0.0248 | | value_loss | 0.000883 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 53.2 | | ep_rew_mean | 0.84 | | time/ | | | fps | 1128 | | iterations | 514 | | time_elapsed | 3732 | | total_timesteps | 4210688 | | train/ | | | approx_kl | 0.059093148 | | clip_fraction | 0.314 | | clip_range | 0.145 | | entropy_loss | -5.62 | | explained_variance | 0.934 | | learning_rate | 0.00024 | | loss | -0.0384 | | n_updates | 2052 | | policy_gradient_loss | -0.0254 | | value_loss | 0.000913 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 54 | | ep_rew_mean | 0.831 | | time/ | | | fps | 1128 | | iterations | 515 | | time_elapsed | 3739 | | total_timesteps | 4218880 | | train/ | | | approx_kl | 0.051317383 | | clip_fraction | 0.334 | | clip_range | 0.145 | | entropy_loss | -5.44 | | explained_variance | 0.929 | | learning_rate | 0.00024 | | loss | -0.0318 | | n_updates | 2056 | | policy_gradient_loss | -0.0223 | | value_loss | 0.000761 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 51.9 | | ep_rew_mean | 0.84 | | time/ | | | fps | 1128 | | iterations | 516 | | time_elapsed | 3746 | | total_timesteps | 4227072 | | train/ | | | approx_kl | 0.05705727 | | clip_fraction | 0.363 | | clip_range | 0.145 | | entropy_loss | -5.47 | | explained_variance | 0.927 | | learning_rate | 0.00024 | | loss | -0.0221 | | n_updates | 2060 | | policy_gradient_loss | -0.0235 | | value_loss | 0.000911 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 51.8 | | ep_rew_mean | 0.833 | | time/ | | | fps | 1128 | | iterations | 517 | | time_elapsed | 3753 | | total_timesteps | 4235264 | | train/ | | | approx_kl | 0.05086074 | | clip_fraction | 0.326 | | clip_range | 0.145 | | entropy_loss | -5.51 | | explained_variance | 0.947 | | learning_rate | 0.00024 | | loss | -0.0361 | | n_updates | 2064 | | policy_gradient_loss | -0.0243 | | value_loss | 0.000655 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 64.7 | | ep_rew_mean | 0.799 | | time/ | | | fps | 1128 | | iterations | 518 | | time_elapsed | 3761 | | total_timesteps | 4243456 | | train/ | | | approx_kl | 0.04305125 | | clip_fraction | 0.365 | | clip_range | 0.145 | | entropy_loss | -5.63 | | explained_variance | 0.95 | | learning_rate | 0.00024 | | loss | -0.0426 | | n_updates | 2068 | | policy_gradient_loss | -0.0278 | | value_loss | 0.000684 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 62.4 | | ep_rew_mean | 0.805 | | time/ | | | fps | 1128 | | iterations | 519 | | time_elapsed | 3768 | | total_timesteps | 4251648 | | train/ | | | approx_kl | 0.054932684 | | clip_fraction | 0.369 | | clip_range | 0.145 | | entropy_loss | -5.87 | | explained_variance | 0.93 | | learning_rate | 0.000239 | | loss | -0.0409 | | n_updates | 2072 | | policy_gradient_loss | -0.0294 | | value_loss | 0.00116 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 53 | | ep_rew_mean | 0.837 | | time/ | | | fps | 1128 | | iterations | 520 | | time_elapsed | 3775 | | total_timesteps | 4259840 | | train/ | | | approx_kl | 0.060865033 | | clip_fraction | 0.368 | | clip_range | 0.145 | | entropy_loss | -5.82 | | explained_variance | 0.941 | | learning_rate | 0.000239 | | loss | -0.0482 | | n_updates | 2076 | | policy_gradient_loss | -0.0306 | | value_loss | 0.000939 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 52.4 | | ep_rew_mean | 0.834 | | time/ | | | fps | 1128 | | iterations | 521 | | time_elapsed | 3782 | | total_timesteps | 4268032 | | train/ | | | approx_kl | 0.056890756 | | clip_fraction | 0.378 | | clip_range | 0.145 | | entropy_loss | -5.68 | | explained_variance | 0.946 | | learning_rate | 0.000239 | | loss | -0.0412 | | n_updates | 2080 | | policy_gradient_loss | -0.0255 | | value_loss | 0.000799 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 61.3 | | ep_rew_mean | 0.808 | | time/ | | | fps | 1128 | | iterations | 522 | | time_elapsed | 3790 | | total_timesteps | 4276224 | | train/ | | | approx_kl | 0.048369084 | | clip_fraction | 0.345 | | clip_range | 0.145 | | entropy_loss | -5.66 | | explained_variance | 0.943 | | learning_rate | 0.000239 | | loss | -0.0382 | | n_updates | 2084 | | policy_gradient_loss | -0.0252 | | value_loss | 0.000792 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 58.9 | | ep_rew_mean | 0.817 | | time/ | | | fps | 1128 | | iterations | 523 | | time_elapsed | 3797 | | total_timesteps | 4284416 | | train/ | | | approx_kl | 0.06315075 | | clip_fraction | 0.38 | | clip_range | 0.145 | | entropy_loss | -5.67 | | explained_variance | 0.955 | | learning_rate | 0.000239 | | loss | -0.041 | | n_updates | 2088 | | policy_gradient_loss | -0.0296 | | value_loss | 0.000681 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 48.7 | | ep_rew_mean | 0.845 | | time/ | | | fps | 1128 | | iterations | 524 | | time_elapsed | 3804 | | total_timesteps | 4292608 | | train/ | | | approx_kl | 0.04851605 | | clip_fraction | 0.354 | | clip_range | 0.145 | | entropy_loss | -5.57 | | explained_variance | 0.928 | | learning_rate | 0.000239 | | loss | -0.0381 | | n_updates | 2092 | | policy_gradient_loss | -0.0246 | | value_loss | 0.000958 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 53.5 | | ep_rew_mean | 0.831 | | time/ | | | fps | 1128 | | iterations | 525 | | time_elapsed | 3812 | | total_timesteps | 4300800 | | train/ | | | approx_kl | 0.052156776 | | clip_fraction | 0.309 | | clip_range | 0.145 | | entropy_loss | -5.44 | | explained_variance | 0.964 | | learning_rate | 0.000239 | | loss | -0.0265 | | n_updates | 2096 | | policy_gradient_loss | -0.0204 | | value_loss | 0.000407 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 56.6 | | ep_rew_mean | 0.82 | | time/ | | | fps | 1128 | | iterations | 526 | | time_elapsed | 3819 | | total_timesteps | 4308992 | | train/ | | | approx_kl | 0.050538268 | | clip_fraction | 0.317 | | clip_range | 0.145 | | entropy_loss | -5.45 | | explained_variance | 0.947 | | learning_rate | 0.000239 | | loss | -0.0394 | | n_updates | 2100 | | policy_gradient_loss | -0.0218 | | value_loss | 0.000639 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 48.2 | | ep_rew_mean | 0.844 | | time/ | | | fps | 1128 | | iterations | 527 | | time_elapsed | 3826 | | total_timesteps | 4317184 | | train/ | | | approx_kl | 0.053843647 | | clip_fraction | 0.372 | | clip_range | 0.145 | | entropy_loss | -5.57 | | explained_variance | 0.934 | | learning_rate | 0.000239 | | loss | -0.032 | | n_updates | 2104 | | policy_gradient_loss | -0.0229 | | value_loss | 0.000952 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 48.1 | | ep_rew_mean | 0.851 | | time/ | | | fps | 1128 | | iterations | 528 | | time_elapsed | 3834 | | total_timesteps | 4325376 | | train/ | | | approx_kl | 0.04266857 | | clip_fraction | 0.285 | | clip_range | 0.145 | | entropy_loss | -5.16 | | explained_variance | 0.9 | | learning_rate | 0.000239 | | loss | -0.0193 | | n_updates | 2108 | | policy_gradient_loss | -0.0141 | | value_loss | 0.00068 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 47.5 | | ep_rew_mean | 0.849 | | time/ | | | fps | 1128 | | iterations | 529 | | time_elapsed | 3841 | | total_timesteps | 4333568 | | train/ | | | approx_kl | 0.036809586 | | clip_fraction | 0.284 | | clip_range | 0.145 | | entropy_loss | -5.19 | | explained_variance | 0.925 | | learning_rate | 0.000239 | | loss | -0.024 | | n_updates | 2112 | | policy_gradient_loss | -0.0173 | | value_loss | 0.000565 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 51.2 | | ep_rew_mean | 0.842 | | time/ | | | fps | 1128 | | iterations | 530 | | time_elapsed | 3848 | | total_timesteps | 4341760 | | train/ | | | approx_kl | 0.045482874 | | clip_fraction | 0.272 | | clip_range | 0.145 | | entropy_loss | -5.21 | | explained_variance | 0.956 | | learning_rate | 0.000239 | | loss | -0.0243 | | n_updates | 2116 | | policy_gradient_loss | -0.0171 | | value_loss | 0.000378 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 54.1 | | ep_rew_mean | 0.836 | | time/ | | | fps | 1128 | | iterations | 531 | | time_elapsed | 3855 | | total_timesteps | 4349952 | | train/ | | | approx_kl | 0.04621696 | | clip_fraction | 0.269 | | clip_range | 0.145 | | entropy_loss | -5.36 | | explained_variance | 0.921 | | learning_rate | 0.000239 | | loss | -0.0243 | | n_updates | 2120 | | policy_gradient_loss | -0.0176 | | value_loss | 0.000705 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 53.5 | | ep_rew_mean | 0.835 | | time/ | | | fps | 1128 | | iterations | 532 | | time_elapsed | 3863 | | total_timesteps | 4358144 | | train/ | | | approx_kl | 0.048687138 | | clip_fraction | 0.344 | | clip_range | 0.145 | | entropy_loss | -5.44 | | explained_variance | 0.911 | | learning_rate | 0.000239 | | loss | -0.035 | | n_updates | 2124 | | policy_gradient_loss | -0.0225 | | value_loss | 0.00107 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 51.5 | | ep_rew_mean | 0.838 | | time/ | | | fps | 1127 | | iterations | 533 | | time_elapsed | 3871 | | total_timesteps | 4366336 | | train/ | | | approx_kl | 0.056407236 | | clip_fraction | 0.314 | | clip_range | 0.145 | | entropy_loss | -5.45 | | explained_variance | 0.965 | | learning_rate | 0.000239 | | loss | -0.0312 | | n_updates | 2128 | | policy_gradient_loss | -0.0217 | | value_loss | 0.000401 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 50.8 | | ep_rew_mean | 0.841 | | time/ | | | fps | 1127 | | iterations | 534 | | time_elapsed | 3878 | | total_timesteps | 4374528 | | train/ | | | approx_kl | 0.045233697 | | clip_fraction | 0.318 | | clip_range | 0.145 | | entropy_loss | -5.31 | | explained_variance | 0.963 | | learning_rate | 0.000239 | | loss | -0.0216 | | n_updates | 2132 | | policy_gradient_loss | -0.0189 | | value_loss | 0.000412 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 52.9 | | ep_rew_mean | 0.838 | | time/ | | | fps | 1127 | | iterations | 535 | | time_elapsed | 3885 | | total_timesteps | 4382720 | | train/ | | | approx_kl | 0.044545967 | | clip_fraction | 0.295 | | clip_range | 0.145 | | entropy_loss | -5.36 | | explained_variance | 0.952 | | learning_rate | 0.000239 | | loss | -0.0367 | | n_updates | 2136 | | policy_gradient_loss | -0.0205 | | value_loss | 0.000591 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 48.1 | | ep_rew_mean | 0.849 | | time/ | | | fps | 1127 | | iterations | 536 | | time_elapsed | 3893 | | total_timesteps | 4390912 | | train/ | | | approx_kl | 0.048472296 | | clip_fraction | 0.315 | | clip_range | 0.145 | | entropy_loss | -5.31 | | explained_variance | 0.939 | | learning_rate | 0.000239 | | loss | -0.0253 | | n_updates | 2140 | | policy_gradient_loss | -0.0207 | | value_loss | 0.000708 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 50.6 | | ep_rew_mean | 0.844 | | time/ | | | fps | 1127 | | iterations | 537 | | time_elapsed | 3900 | | total_timesteps | 4399104 | | train/ | | | approx_kl | 0.029288147 | | clip_fraction | 0.272 | | clip_range | 0.145 | | entropy_loss | -5.11 | | explained_variance | 0.967 | | learning_rate | 0.000239 | | loss | -0.0203 | | n_updates | 2144 | | policy_gradient_loss | -0.0117 | | value_loss | 0.000244 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 49.2 | | ep_rew_mean | 0.844 | | time/ | | | fps | 1127 | | iterations | 538 | | time_elapsed | 3907 | | total_timesteps | 4407296 | | train/ | | | approx_kl | 0.05622423 | | clip_fraction | 0.341 | | clip_range | 0.145 | | entropy_loss | -5.28 | | explained_variance | 0.956 | | learning_rate | 0.000239 | | loss | -0.0254 | | n_updates | 2148 | | policy_gradient_loss | -0.0174 | | value_loss | 0.000445 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 51.6 | | ep_rew_mean | 0.833 | | time/ | | | fps | 1127 | | iterations | 539 | | time_elapsed | 3914 | | total_timesteps | 4415488 | | train/ | | | approx_kl | 0.057715148 | | clip_fraction | 0.288 | | clip_range | 0.144 | | entropy_loss | -5.28 | | explained_variance | 0.963 | | learning_rate | 0.000239 | | loss | -0.026 | | n_updates | 2152 | | policy_gradient_loss | -0.0178 | | value_loss | 0.000341 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 53.2 | | ep_rew_mean | 0.826 | | time/ | | | fps | 1127 | | iterations | 540 | | time_elapsed | 3922 | | total_timesteps | 4423680 | | train/ | | | approx_kl | 0.056498893 | | clip_fraction | 0.328 | | clip_range | 0.144 | | entropy_loss | -5.32 | | explained_variance | 0.951 | | learning_rate | 0.000239 | | loss | -0.0306 | | n_updates | 2156 | | policy_gradient_loss | -0.0207 | | value_loss | 0.000491 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 53.7 | | ep_rew_mean | 0.837 | | time/ | | | fps | 1127 | | iterations | 541 | | time_elapsed | 3929 | | total_timesteps | 4431872 | | train/ | | | approx_kl | 0.099204816 | | clip_fraction | 0.329 | | clip_range | 0.144 | | entropy_loss | -5.37 | | explained_variance | 0.957 | | learning_rate | 0.000239 | | loss | -0.0271 | | n_updates | 2160 | | policy_gradient_loss | -0.0224 | | value_loss | 0.000486 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 51.3 | | ep_rew_mean | 0.832 | | time/ | | | fps | 1127 | | iterations | 542 | | time_elapsed | 3936 | | total_timesteps | 4440064 | | train/ | | | approx_kl | 0.05608494 | | clip_fraction | 0.32 | | clip_range | 0.144 | | entropy_loss | -5.44 | | explained_variance | 0.944 | | learning_rate | 0.000239 | | loss | -0.0224 | | n_updates | 2164 | | policy_gradient_loss | -0.0215 | | value_loss | 0.000704 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 53.7 | | ep_rew_mean | 0.838 | | time/ | | | fps | 1127 | | iterations | 543 | | time_elapsed | 3943 | | total_timesteps | 4448256 | | train/ | | | approx_kl | 0.060483634 | | clip_fraction | 0.305 | | clip_range | 0.144 | | entropy_loss | -5.33 | | explained_variance | 0.946 | | learning_rate | 0.000239 | | loss | -0.0199 | | n_updates | 2168 | | policy_gradient_loss | -0.0159 | | value_loss | 0.000516 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 49.7 | | ep_rew_mean | 0.841 | | time/ | | | fps | 1127 | | iterations | 544 | | time_elapsed | 3950 | | total_timesteps | 4456448 | | train/ | | | approx_kl | 0.054039173 | | clip_fraction | 0.34 | | clip_range | 0.144 | | entropy_loss | -5.53 | | explained_variance | 0.943 | | learning_rate | 0.000239 | | loss | -0.0368 | | n_updates | 2172 | | policy_gradient_loss | -0.0242 | | value_loss | 0.000641 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 54 | | ep_rew_mean | 0.837 | | time/ | | | fps | 1127 | | iterations | 545 | | time_elapsed | 3958 | | total_timesteps | 4464640 | | train/ | | | approx_kl | 0.040369354 | | clip_fraction | 0.347 | | clip_range | 0.144 | | entropy_loss | -5.54 | | explained_variance | 0.944 | | learning_rate | 0.000239 | | loss | -0.0289 | | n_updates | 2176 | | policy_gradient_loss | -0.0221 | | value_loss | 0.000656 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 53.7 | | ep_rew_mean | 0.839 | | time/ | | | fps | 1127 | | iterations | 546 | | time_elapsed | 3965 | | total_timesteps | 4472832 | | train/ | | | approx_kl | 0.045313485 | | clip_fraction | 0.316 | | clip_range | 0.144 | | entropy_loss | -5.5 | | explained_variance | 0.924 | | learning_rate | 0.000239 | | loss | -0.0236 | | n_updates | 2180 | | policy_gradient_loss | -0.0206 | | value_loss | 0.000853 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 55.1 | | ep_rew_mean | 0.837 | | time/ | | | fps | 1127 | | iterations | 547 | | time_elapsed | 3972 | | total_timesteps | 4481024 | | train/ | | | approx_kl | 0.046372186 | | clip_fraction | 0.324 | | clip_range | 0.144 | | entropy_loss | -5.56 | | explained_variance | 0.921 | | learning_rate | 0.000239 | | loss | -0.0331 | | n_updates | 2184 | | policy_gradient_loss | -0.0193 | | value_loss | 0.000983 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 50.6 | | ep_rew_mean | 0.843 | | time/ | | | fps | 1127 | | iterations | 548 | | time_elapsed | 3980 | | total_timesteps | 4489216 | | train/ | | | approx_kl | 0.04603003 | | clip_fraction | 0.309 | | clip_range | 0.144 | | entropy_loss | -5.72 | | explained_variance | 0.936 | | learning_rate | 0.000239 | | loss | -0.0305 | | n_updates | 2188 | | policy_gradient_loss | -0.0249 | | value_loss | 0.000799 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 55.3 | | ep_rew_mean | 0.825 | | time/ | | | fps | 1127 | | iterations | 549 | | time_elapsed | 3987 | | total_timesteps | 4497408 | | train/ | | | approx_kl | 0.058056153 | | clip_fraction | 0.373 | | clip_range | 0.144 | | entropy_loss | -5.68 | | explained_variance | 0.929 | | learning_rate | 0.000239 | | loss | -0.0413 | | n_updates | 2192 | | policy_gradient_loss | -0.0235 | | value_loss | 0.000888 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 53.3 | | ep_rew_mean | 0.83 | | time/ | | | fps | 1127 | | iterations | 550 | | time_elapsed | 3995 | | total_timesteps | 4505600 | | train/ | | | approx_kl | 0.043329276 | | clip_fraction | 0.31 | | clip_range | 0.144 | | entropy_loss | -5.65 | | explained_variance | 0.939 | | learning_rate | 0.000239 | | loss | -0.0357 | | n_updates | 2196 | | policy_gradient_loss | -0.0251 | | value_loss | 0.000719 | ----------------------------------------- --------------------------------------- | rollout/ | | | ep_len_mean | 57.3 | | ep_rew_mean | 0.82 | | time/ | | | fps | 1127 | | iterations | 551 | | time_elapsed | 4002 | | total_timesteps | 4513792 | | train/ | | | approx_kl | 0.0553881 | | clip_fraction | 0.338 | | clip_range | 0.144 | | entropy_loss | -5.52 | | explained_variance | 0.925 | | learning_rate | 0.000239 | | loss | -0.0327 | | n_updates | 2200 | | policy_gradient_loss | -0.02 | | value_loss | 0.000878 | --------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 51.8 | | ep_rew_mean | 0.839 | | time/ | | | fps | 1127 | | iterations | 552 | | time_elapsed | 4010 | | total_timesteps | 4521984 | | train/ | | | approx_kl | 0.05924145 | | clip_fraction | 0.334 | | clip_range | 0.144 | | entropy_loss | -5.57 | | explained_variance | 0.948 | | learning_rate | 0.000239 | | loss | -0.0355 | | n_updates | 2204 | | policy_gradient_loss | -0.0247 | | value_loss | 0.000671 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 55.9 | | ep_rew_mean | 0.834 | | time/ | | | fps | 1127 | | iterations | 553 | | time_elapsed | 4017 | | total_timesteps | 4530176 | | train/ | | | approx_kl | 0.045635074 | | clip_fraction | 0.326 | | clip_range | 0.144 | | entropy_loss | -5.44 | | explained_variance | 0.937 | | learning_rate | 0.000239 | | loss | -0.0317 | | n_updates | 2208 | | policy_gradient_loss | -0.0199 | | value_loss | 0.000695 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 49.5 | | ep_rew_mean | 0.844 | | time/ | | | fps | 1127 | | iterations | 554 | | time_elapsed | 4024 | | total_timesteps | 4538368 | | train/ | | | approx_kl | 0.050881866 | | clip_fraction | 0.308 | | clip_range | 0.144 | | entropy_loss | -5.49 | | explained_variance | 0.95 | | learning_rate | 0.000239 | | loss | -0.0351 | | n_updates | 2212 | | policy_gradient_loss | -0.0213 | | value_loss | 0.000575 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 48.5 | | ep_rew_mean | 0.841 | | time/ | | | fps | 1127 | | iterations | 555 | | time_elapsed | 4032 | | total_timesteps | 4546560 | | train/ | | | approx_kl | 0.044513717 | | clip_fraction | 0.292 | | clip_range | 0.144 | | entropy_loss | -5.29 | | explained_variance | 0.956 | | learning_rate | 0.000239 | | loss | -0.0221 | | n_updates | 2216 | | policy_gradient_loss | -0.0163 | | value_loss | 0.000371 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 49.5 | | ep_rew_mean | 0.842 | | time/ | | | fps | 1127 | | iterations | 556 | | time_elapsed | 4039 | | total_timesteps | 4554752 | | train/ | | | approx_kl | 0.038221274 | | clip_fraction | 0.318 | | clip_range | 0.144 | | entropy_loss | -5.25 | | explained_variance | 0.964 | | learning_rate | 0.000239 | | loss | -0.0272 | | n_updates | 2220 | | policy_gradient_loss | -0.0183 | | value_loss | 0.000332 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 46.6 | | ep_rew_mean | 0.852 | | time/ | | | fps | 1127 | | iterations | 557 | | time_elapsed | 4046 | | total_timesteps | 4562944 | | train/ | | | approx_kl | 0.05330053 | | clip_fraction | 0.222 | | clip_range | 0.144 | | entropy_loss | -5.25 | | explained_variance | 0.987 | | learning_rate | 0.000239 | | loss | -0.027 | | n_updates | 2224 | | policy_gradient_loss | -0.0192 | | value_loss | 0.000112 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 47.4 | | ep_rew_mean | 0.848 | | time/ | | | fps | 1127 | | iterations | 558 | | time_elapsed | 4054 | | total_timesteps | 4571136 | | train/ | | | approx_kl | 0.031342708 | | clip_fraction | 0.273 | | clip_range | 0.144 | | entropy_loss | -5.12 | | explained_variance | 0.954 | | learning_rate | 0.000239 | | loss | -0.0092 | | n_updates | 2228 | | policy_gradient_loss | -0.00933 | | value_loss | 0.000303 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 52.5 | | ep_rew_mean | 0.833 | | time/ | | | fps | 1127 | | iterations | 559 | | time_elapsed | 4061 | | total_timesteps | 4579328 | | train/ | | | approx_kl | 0.042512417 | | clip_fraction | 0.285 | | clip_range | 0.144 | | entropy_loss | -5.22 | | explained_variance | 0.961 | | learning_rate | 0.000239 | | loss | -0.0322 | | n_updates | 2232 | | policy_gradient_loss | -0.0216 | | value_loss | 0.0003 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 47.2 | | ep_rew_mean | 0.85 | | time/ | | | fps | 1127 | | iterations | 560 | | time_elapsed | 4068 | | total_timesteps | 4587520 | | train/ | | | approx_kl | 0.051497437 | | clip_fraction | 0.324 | | clip_range | 0.144 | | entropy_loss | -5.28 | | explained_variance | 0.939 | | learning_rate | 0.000239 | | loss | -0.02 | | n_updates | 2236 | | policy_gradient_loss | -0.0192 | | value_loss | 0.000622 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 48.5 | | ep_rew_mean | 0.848 | | time/ | | | fps | 1127 | | iterations | 561 | | time_elapsed | 4075 | | total_timesteps | 4595712 | | train/ | | | approx_kl | 0.040752567 | | clip_fraction | 0.291 | | clip_range | 0.144 | | entropy_loss | -5.18 | | explained_variance | 0.965 | | learning_rate | 0.000239 | | loss | -0.0173 | | n_updates | 2240 | | policy_gradient_loss | -0.0153 | | value_loss | 0.000251 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 48.3 | | ep_rew_mean | 0.851 | | time/ | | | fps | 1127 | | iterations | 562 | | time_elapsed | 4082 | | total_timesteps | 4603904 | | train/ | | | approx_kl | 0.05736787 | | clip_fraction | 0.284 | | clip_range | 0.144 | | entropy_loss | -5.14 | | explained_variance | 0.937 | | learning_rate | 0.000239 | | loss | -0.0194 | | n_updates | 2244 | | policy_gradient_loss | -0.0148 | | value_loss | 0.000487 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 46 | | ep_rew_mean | 0.853 | | time/ | | | fps | 1127 | | iterations | 563 | | time_elapsed | 4090 | | total_timesteps | 4612096 | | train/ | | | approx_kl | 0.06195868 | | clip_fraction | 0.264 | | clip_range | 0.144 | | entropy_loss | -5.07 | | explained_variance | 0.962 | | learning_rate | 0.000239 | | loss | -0.0137 | | n_updates | 2248 | | policy_gradient_loss | -0.014 | | value_loss | 0.000254 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 49.4 | | ep_rew_mean | 0.841 | | time/ | | | fps | 1127 | | iterations | 564 | | time_elapsed | 4097 | | total_timesteps | 4620288 | | train/ | | | approx_kl | 0.012728315 | | clip_fraction | 0.187 | | clip_range | 0.144 | | entropy_loss | -4.98 | | explained_variance | 0.99 | | learning_rate | 0.000239 | | loss | -0.00338 | | n_updates | 2252 | | policy_gradient_loss | -0.00427 | | value_loss | 4.72e-05 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 48.2 | | ep_rew_mean | 0.849 | | time/ | | | fps | 1127 | | iterations | 565 | | time_elapsed | 4105 | | total_timesteps | 4628480 | | train/ | | | approx_kl | 0.040523097 | | clip_fraction | 0.273 | | clip_range | 0.144 | | entropy_loss | -5.06 | | explained_variance | 0.971 | | learning_rate | 0.000239 | | loss | -0.0208 | | n_updates | 2256 | | policy_gradient_loss | -0.0156 | | value_loss | 0.000235 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 46 | | ep_rew_mean | 0.853 | | time/ | | | fps | 1127 | | iterations | 566 | | time_elapsed | 4112 | | total_timesteps | 4636672 | | train/ | | | approx_kl | 0.041711353 | | clip_fraction | 0.261 | | clip_range | 0.144 | | entropy_loss | -4.96 | | explained_variance | 0.98 | | learning_rate | 0.000239 | | loss | -0.0171 | | n_updates | 2260 | | policy_gradient_loss | -0.013 | | value_loss | 0.000143 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 49.8 | | ep_rew_mean | 0.846 | | time/ | | | fps | 1127 | | iterations | 567 | | time_elapsed | 4119 | | total_timesteps | 4644864 | | train/ | | | approx_kl | 0.012162924 | | clip_fraction | 0.238 | | clip_range | 0.144 | | entropy_loss | -4.93 | | explained_variance | 0.978 | | learning_rate | 0.000239 | | loss | -0.00674 | | n_updates | 2264 | | policy_gradient_loss | -0.00447 | | value_loss | 0.000113 | ----------------------------------------- --------------------------------------- | rollout/ | | | ep_len_mean | 46 | | ep_rew_mean | 0.853 | | time/ | | | fps | 1127 | | iterations | 568 | | time_elapsed | 4126 | | total_timesteps | 4653056 | | train/ | | | approx_kl | 0.0406085 | | clip_fraction | 0.314 | | clip_range | 0.144 | | entropy_loss | -5.02 | | explained_variance | 0.952 | | learning_rate | 0.000239 | | loss | -0.027 | | n_updates | 2268 | | policy_gradient_loss | -0.0153 | | value_loss | 0.000354 | --------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 49.7 | | ep_rew_mean | 0.847 | | time/ | | | fps | 1127 | | iterations | 569 | | time_elapsed | 4134 | | total_timesteps | 4661248 | | train/ | | | approx_kl | 0.05196093 | | clip_fraction | 0.27 | | clip_range | 0.144 | | entropy_loss | -4.93 | | explained_variance | 0.932 | | learning_rate | 0.000238 | | loss | -0.0135 | | n_updates | 2272 | | policy_gradient_loss | -0.0121 | | value_loss | 0.000424 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 47.9 | | ep_rew_mean | 0.848 | | time/ | | | fps | 1127 | | iterations | 570 | | time_elapsed | 4141 | | total_timesteps | 4669440 | | train/ | | | approx_kl | 0.04596716 | | clip_fraction | 0.254 | | clip_range | 0.144 | | entropy_loss | -4.98 | | explained_variance | 0.961 | | learning_rate | 0.000238 | | loss | -0.0198 | | n_updates | 2276 | | policy_gradient_loss | -0.0167 | | value_loss | 0.00028 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 48.2 | | ep_rew_mean | 0.848 | | time/ | | | fps | 1127 | | iterations | 571 | | time_elapsed | 4148 | | total_timesteps | 4677632 | | train/ | | | approx_kl | 0.023760594 | | clip_fraction | 0.237 | | clip_range | 0.144 | | entropy_loss | -4.86 | | explained_variance | 0.969 | | learning_rate | 0.000238 | | loss | -0.00121 | | n_updates | 2280 | | policy_gradient_loss | -0.00792 | | value_loss | 0.000183 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 46.3 | | ep_rew_mean | 0.854 | | time/ | | | fps | 1127 | | iterations | 572 | | time_elapsed | 4156 | | total_timesteps | 4685824 | | train/ | | | approx_kl | 0.04906841 | | clip_fraction | 0.284 | | clip_range | 0.144 | | entropy_loss | -4.95 | | explained_variance | 0.963 | | learning_rate | 0.000238 | | loss | -0.0207 | | n_updates | 2284 | | policy_gradient_loss | -0.0133 | | value_loss | 0.000272 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 46 | | ep_rew_mean | 0.853 | | time/ | | | fps | 1127 | | iterations | 573 | | time_elapsed | 4163 | | total_timesteps | 4694016 | | train/ | | | approx_kl | 0.029961895 | | clip_fraction | 0.262 | | clip_range | 0.144 | | entropy_loss | -4.99 | | explained_variance | 0.947 | | learning_rate | 0.000238 | | loss | -0.0223 | | n_updates | 2288 | | policy_gradient_loss | -0.0112 | | value_loss | 0.000373 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 49.7 | | ep_rew_mean | 0.847 | | time/ | | | fps | 1127 | | iterations | 574 | | time_elapsed | 4171 | | total_timesteps | 4702208 | | train/ | | | approx_kl | 0.071192876 | | clip_fraction | 0.19 | | clip_range | 0.144 | | entropy_loss | -5 | | explained_variance | 0.985 | | learning_rate | 0.000238 | | loss | -0.0133 | | n_updates | 2292 | | policy_gradient_loss | -0.0121 | | value_loss | 8.15e-05 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 49.8 | | ep_rew_mean | 0.841 | | time/ | | | fps | 1127 | | iterations | 575 | | time_elapsed | 4178 | | total_timesteps | 4710400 | | train/ | | | approx_kl | 0.059241414 | | clip_fraction | 0.291 | | clip_range | 0.144 | | entropy_loss | -5.05 | | explained_variance | 0.967 | | learning_rate | 0.000238 | | loss | -0.0201 | | n_updates | 2296 | | policy_gradient_loss | -0.0169 | | value_loss | 0.000278 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 50.9 | | ep_rew_mean | 0.838 | | time/ | | | fps | 1127 | | iterations | 576 | | time_elapsed | 4185 | | total_timesteps | 4718592 | | train/ | | | approx_kl | 0.04245595 | | clip_fraction | 0.258 | | clip_range | 0.144 | | entropy_loss | -5.11 | | explained_variance | 0.957 | | learning_rate | 0.000238 | | loss | -0.0205 | | n_updates | 2300 | | policy_gradient_loss | -0.0169 | | value_loss | 0.000339 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 47.2 | | ep_rew_mean | 0.852 | | time/ | | | fps | 1127 | | iterations | 577 | | time_elapsed | 4193 | | total_timesteps | 4726784 | | train/ | | | approx_kl | 0.05366593 | | clip_fraction | 0.322 | | clip_range | 0.144 | | entropy_loss | -5.11 | | explained_variance | 0.948 | | learning_rate | 0.000238 | | loss | -0.0249 | | n_updates | 2304 | | policy_gradient_loss | -0.0192 | | value_loss | 0.000503 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 46 | | ep_rew_mean | 0.853 | | time/ | | | fps | 1127 | | iterations | 578 | | time_elapsed | 4200 | | total_timesteps | 4734976 | | train/ | | | approx_kl | 0.031565104 | | clip_fraction | 0.219 | | clip_range | 0.144 | | entropy_loss | -5.03 | | explained_variance | 0.968 | | learning_rate | 0.000238 | | loss | -0.0143 | | n_updates | 2308 | | policy_gradient_loss | -0.0117 | | value_loss | 0.000195 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 47.8 | | ep_rew_mean | 0.846 | | time/ | | | fps | 1127 | | iterations | 579 | | time_elapsed | 4207 | | total_timesteps | 4743168 | | train/ | | | approx_kl | 0.02470883 | | clip_fraction | 0.227 | | clip_range | 0.144 | | entropy_loss | -5.02 | | explained_variance | 0.988 | | learning_rate | 0.000238 | | loss | -0.0161 | | n_updates | 2312 | | policy_gradient_loss | -0.00843 | | value_loss | 8.33e-05 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 49 | | ep_rew_mean | 0.845 | | time/ | | | fps | 1127 | | iterations | 580 | | time_elapsed | 4215 | | total_timesteps | 4751360 | | train/ | | | approx_kl | 0.032272242 | | clip_fraction | 0.263 | | clip_range | 0.144 | | entropy_loss | -5.11 | | explained_variance | 0.966 | | learning_rate | 0.000238 | | loss | -0.0185 | | n_updates | 2316 | | policy_gradient_loss | -0.0137 | | value_loss | 0.000273 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 47.9 | | ep_rew_mean | 0.85 | | time/ | | | fps | 1127 | | iterations | 581 | | time_elapsed | 4222 | | total_timesteps | 4759552 | | train/ | | | approx_kl | 0.043851785 | | clip_fraction | 0.27 | | clip_range | 0.144 | | entropy_loss | -5.18 | | explained_variance | 0.966 | | learning_rate | 0.000238 | | loss | -0.0229 | | n_updates | 2320 | | policy_gradient_loss | -0.0172 | | value_loss | 0.000309 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 49.2 | | ep_rew_mean | 0.841 | | time/ | | | fps | 1127 | | iterations | 582 | | time_elapsed | 4229 | | total_timesteps | 4767744 | | train/ | | | approx_kl | 0.042000175 | | clip_fraction | 0.211 | | clip_range | 0.144 | | entropy_loss | -5.07 | | explained_variance | 0.946 | | learning_rate | 0.000238 | | loss | -0.0173 | | n_updates | 2324 | | policy_gradient_loss | -0.0103 | | value_loss | 0.000322 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 48.9 | | ep_rew_mean | 0.848 | | time/ | | | fps | 1127 | | iterations | 583 | | time_elapsed | 4237 | | total_timesteps | 4775936 | | train/ | | | approx_kl | 0.04437423 | | clip_fraction | 0.302 | | clip_range | 0.144 | | entropy_loss | -5.21 | | explained_variance | 0.953 | | learning_rate | 0.000238 | | loss | -0.028 | | n_updates | 2328 | | policy_gradient_loss | -0.021 | | value_loss | 0.000431 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 46.4 | | ep_rew_mean | 0.853 | | time/ | | | fps | 1127 | | iterations | 584 | | time_elapsed | 4244 | | total_timesteps | 4784128 | | train/ | | | approx_kl | 0.06473155 | | clip_fraction | 0.2 | | clip_range | 0.144 | | entropy_loss | -5.19 | | explained_variance | 0.988 | | learning_rate | 0.000238 | | loss | -0.0214 | | n_updates | 2332 | | policy_gradient_loss | -0.0176 | | value_loss | 9.54e-05 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 50.8 | | ep_rew_mean | 0.837 | | time/ | | | fps | 1127 | | iterations | 585 | | time_elapsed | 4251 | | total_timesteps | 4792320 | | train/ | | | approx_kl | 0.028169803 | | clip_fraction | 0.211 | | clip_range | 0.144 | | entropy_loss | -5.05 | | explained_variance | 0.959 | | learning_rate | 0.000238 | | loss | -0.0098 | | n_updates | 2336 | | policy_gradient_loss | -0.00858 | | value_loss | 0.000206 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 52.5 | | ep_rew_mean | 0.839 | | time/ | | | fps | 1127 | | iterations | 586 | | time_elapsed | 4258 | | total_timesteps | 4800512 | | train/ | | | approx_kl | 0.04271345 | | clip_fraction | 0.257 | | clip_range | 0.144 | | entropy_loss | -5.2 | | explained_variance | 0.949 | | learning_rate | 0.000238 | | loss | -0.0275 | | n_updates | 2340 | | policy_gradient_loss | -0.0198 | | value_loss | 0.000402 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 51.4 | | ep_rew_mean | 0.84 | | time/ | | | fps | 1127 | | iterations | 587 | | time_elapsed | 4265 | | total_timesteps | 4808704 | | train/ | | | approx_kl | 0.060102172 | | clip_fraction | 0.286 | | clip_range | 0.144 | | entropy_loss | -5.29 | | explained_variance | 0.942 | | learning_rate | 0.000238 | | loss | -0.0263 | | n_updates | 2344 | | policy_gradient_loss | -0.0195 | | value_loss | 0.000552 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 47.6 | | ep_rew_mean | 0.853 | | time/ | | | fps | 1127 | | iterations | 588 | | time_elapsed | 4273 | | total_timesteps | 4816896 | | train/ | | | approx_kl | 0.04491703 | | clip_fraction | 0.305 | | clip_range | 0.144 | | entropy_loss | -5.26 | | explained_variance | 0.927 | | learning_rate | 0.000238 | | loss | -0.0324 | | n_updates | 2348 | | policy_gradient_loss | -0.0189 | | value_loss | 0.000773 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 48.6 | | ep_rew_mean | 0.839 | | time/ | | | fps | 1127 | | iterations | 589 | | time_elapsed | 4280 | | total_timesteps | 4825088 | | train/ | | | approx_kl | 0.041739043 | | clip_fraction | 0.282 | | clip_range | 0.144 | | entropy_loss | -5.1 | | explained_variance | 0.943 | | learning_rate | 0.000238 | | loss | -0.0149 | | n_updates | 2352 | | policy_gradient_loss | -0.0146 | | value_loss | 0.000447 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 49.1 | | ep_rew_mean | 0.849 | | time/ | | | fps | 1127 | | iterations | 590 | | time_elapsed | 4287 | | total_timesteps | 4833280 | | train/ | | | approx_kl | 0.034513783 | | clip_fraction | 0.253 | | clip_range | 0.144 | | entropy_loss | -5.08 | | explained_variance | 0.961 | | learning_rate | 0.000238 | | loss | -0.0197 | | n_updates | 2356 | | policy_gradient_loss | -0.0143 | | value_loss | 0.000268 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 56 | | ep_rew_mean | 0.835 | | time/ | | | fps | 1127 | | iterations | 591 | | time_elapsed | 4294 | | total_timesteps | 4841472 | | train/ | | | approx_kl | 0.049036443 | | clip_fraction | 0.302 | | clip_range | 0.144 | | entropy_loss | -5.14 | | explained_variance | 0.933 | | learning_rate | 0.000238 | | loss | -0.0181 | | n_updates | 2360 | | policy_gradient_loss | -0.0154 | | value_loss | 0.000599 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 52.5 | | ep_rew_mean | 0.838 | | time/ | | | fps | 1127 | | iterations | 592 | | time_elapsed | 4301 | | total_timesteps | 4849664 | | train/ | | | approx_kl | 0.04551503 | | clip_fraction | 0.277 | | clip_range | 0.144 | | entropy_loss | -5.39 | | explained_variance | 0.943 | | learning_rate | 0.000238 | | loss | -0.0296 | | n_updates | 2364 | | policy_gradient_loss | -0.0225 | | value_loss | 0.000593 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 49.5 | | ep_rew_mean | 0.846 | | time/ | | | fps | 1127 | | iterations | 593 | | time_elapsed | 4309 | | total_timesteps | 4857856 | | train/ | | | approx_kl | 0.036793385 | | clip_fraction | 0.264 | | clip_range | 0.144 | | entropy_loss | -5.28 | | explained_variance | 0.922 | | learning_rate | 0.000238 | | loss | -0.0238 | | n_updates | 2368 | | policy_gradient_loss | -0.0181 | | value_loss | 0.000752 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 54.6 | | ep_rew_mean | 0.837 | | time/ | | | fps | 1127 | | iterations | 594 | | time_elapsed | 4316 | | total_timesteps | 4866048 | | train/ | | | approx_kl | 0.038997218 | | clip_fraction | 0.278 | | clip_range | 0.144 | | entropy_loss | -5.3 | | explained_variance | 0.939 | | learning_rate | 0.000238 | | loss | -0.0298 | | n_updates | 2372 | | policy_gradient_loss | -0.0202 | | value_loss | 0.000543 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 50 | | ep_rew_mean | 0.841 | | time/ | | | fps | 1127 | | iterations | 595 | | time_elapsed | 4324 | | total_timesteps | 4874240 | | train/ | | | approx_kl | 0.04145226 | | clip_fraction | 0.266 | | clip_range | 0.144 | | entropy_loss | -5.39 | | explained_variance | 0.938 | | learning_rate | 0.000238 | | loss | -0.0356 | | n_updates | 2376 | | policy_gradient_loss | -0.0226 | | value_loss | 0.000628 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 50 | | ep_rew_mean | 0.849 | | time/ | | | fps | 1127 | | iterations | 596 | | time_elapsed | 4331 | | total_timesteps | 4882432 | | train/ | | | approx_kl | 0.03622244 | | clip_fraction | 0.259 | | clip_range | 0.144 | | entropy_loss | -5.42 | | explained_variance | 0.927 | | learning_rate | 0.000238 | | loss | -0.0194 | | n_updates | 2380 | | policy_gradient_loss | -0.0217 | | value_loss | 0.000716 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 47.7 | | ep_rew_mean | 0.851 | | time/ | | | fps | 1127 | | iterations | 597 | | time_elapsed | 4338 | | total_timesteps | 4890624 | | train/ | | | approx_kl | 0.046796452 | | clip_fraction | 0.298 | | clip_range | 0.144 | | entropy_loss | -5.48 | | explained_variance | 0.915 | | learning_rate | 0.000238 | | loss | -0.026 | | n_updates | 2384 | | policy_gradient_loss | -0.0208 | | value_loss | 0.000958 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 51.4 | | ep_rew_mean | 0.841 | | time/ | | | fps | 1127 | | iterations | 598 | | time_elapsed | 4346 | | total_timesteps | 4898816 | | train/ | | | approx_kl | 0.043412667 | | clip_fraction | 0.283 | | clip_range | 0.144 | | entropy_loss | -5.38 | | explained_variance | 0.922 | | learning_rate | 0.000238 | | loss | -0.0255 | | n_updates | 2388 | | policy_gradient_loss | -0.0183 | | value_loss | 0.000754 | ----------------------------------------- --------------------------------------- | rollout/ | | | ep_len_mean | 48 | | ep_rew_mean | 0.849 | | time/ | | | fps | 1127 | | iterations | 599 | | time_elapsed | 4353 | | total_timesteps | 4907008 | | train/ | | | approx_kl | 0.0567594 | | clip_fraction | 0.33 | | clip_range | 0.144 | | entropy_loss | -5.44 | | explained_variance | 0.928 | | learning_rate | 0.000238 | | loss | -0.0359 | | n_updates | 2392 | | policy_gradient_loss | -0.0242 | | value_loss | 0.000839 | --------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 48.9 | | ep_rew_mean | 0.85 | | time/ | | | fps | 1127 | | iterations | 600 | | time_elapsed | 4360 | | total_timesteps | 4915200 | | train/ | | | approx_kl | 0.03798549 | | clip_fraction | 0.276 | | clip_range | 0.144 | | entropy_loss | -5.35 | | explained_variance | 0.955 | | learning_rate | 0.000238 | | loss | -0.0296 | | n_updates | 2396 | | policy_gradient_loss | -0.0199 | | value_loss | 0.00045 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 49.1 | | ep_rew_mean | 0.839 | | time/ | | | fps | 1127 | | iterations | 601 | | time_elapsed | 4368 | | total_timesteps | 4923392 | | train/ | | | approx_kl | 0.04307291 | | clip_fraction | 0.294 | | clip_range | 0.144 | | entropy_loss | -5.24 | | explained_variance | 0.914 | | learning_rate | 0.000238 | | loss | -0.023 | | n_updates | 2400 | | policy_gradient_loss | -0.0154 | | value_loss | 0.000658 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 53.6 | | ep_rew_mean | 0.821 | | time/ | | | fps | 1126 | | iterations | 602 | | time_elapsed | 4376 | | total_timesteps | 4931584 | | train/ | | | approx_kl | 0.041731633 | | clip_fraction | 0.241 | | clip_range | 0.144 | | entropy_loss | -5.23 | | explained_variance | 0.967 | | learning_rate | 0.000238 | | loss | -0.0262 | | n_updates | 2404 | | policy_gradient_loss | -0.0165 | | value_loss | 0.000263 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 49.9 | | ep_rew_mean | 0.842 | | time/ | | | fps | 1126 | | iterations | 603 | | time_elapsed | 4383 | | total_timesteps | 4939776 | | train/ | | | approx_kl | 0.047130298 | | clip_fraction | 0.293 | | clip_range | 0.144 | | entropy_loss | -5.28 | | explained_variance | 0.96 | | learning_rate | 0.000238 | | loss | -0.0275 | | n_updates | 2408 | | policy_gradient_loss | -0.0216 | | value_loss | 0.000422 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 46.6 | | ep_rew_mean | 0.855 | | time/ | | | fps | 1126 | | iterations | 604 | | time_elapsed | 4390 | | total_timesteps | 4947968 | | train/ | | | approx_kl | 0.046567023 | | clip_fraction | 0.3 | | clip_range | 0.144 | | entropy_loss | -5.23 | | explained_variance | 0.972 | | learning_rate | 0.000238 | | loss | -0.0281 | | n_updates | 2412 | | policy_gradient_loss | -0.0181 | | value_loss | 0.000268 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 48.6 | | ep_rew_mean | 0.85 | | time/ | | | fps | 1126 | | iterations | 605 | | time_elapsed | 4398 | | total_timesteps | 4956160 | | train/ | | | approx_kl | 0.05410557 | | clip_fraction | 0.29 | | clip_range | 0.144 | | entropy_loss | -5.19 | | explained_variance | 0.935 | | learning_rate | 0.000238 | | loss | -0.0216 | | n_updates | 2416 | | policy_gradient_loss | -0.0166 | | value_loss | 0.000467 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 47.9 | | ep_rew_mean | 0.846 | | time/ | | | fps | 1126 | | iterations | 606 | | time_elapsed | 4405 | | total_timesteps | 4964352 | | train/ | | | approx_kl | 0.03432851 | | clip_fraction | 0.27 | | clip_range | 0.144 | | entropy_loss | -5.27 | | explained_variance | 0.961 | | learning_rate | 0.000238 | | loss | -0.027 | | n_updates | 2420 | | policy_gradient_loss | -0.0181 | | value_loss | 0.00034 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 47.9 | | ep_rew_mean | 0.846 | | time/ | | | fps | 1126 | | iterations | 607 | | time_elapsed | 4412 | | total_timesteps | 4972544 | | train/ | | | approx_kl | 0.030450588 | | clip_fraction | 0.233 | | clip_range | 0.144 | | entropy_loss | -5.18 | | explained_variance | 0.98 | | learning_rate | 0.000238 | | loss | -0.0157 | | n_updates | 2424 | | policy_gradient_loss | -0.0135 | | value_loss | 0.000146 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 48.1 | | ep_rew_mean | 0.849 | | time/ | | | fps | 1126 | | iterations | 608 | | time_elapsed | 4419 | | total_timesteps | 4980736 | | train/ | | | approx_kl | 0.11981427 | | clip_fraction | 0.282 | | clip_range | 0.144 | | entropy_loss | -5.21 | | explained_variance | 0.954 | | learning_rate | 0.000238 | | loss | -0.0237 | | n_updates | 2428 | | policy_gradient_loss | -0.0177 | | value_loss | 0.000402 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 46.2 | | ep_rew_mean | 0.854 | | time/ | | | fps | 1126 | | iterations | 609 | | time_elapsed | 4427 | | total_timesteps | 4988928 | | train/ | | | approx_kl | 0.06815045 | | clip_fraction | 0.236 | | clip_range | 0.144 | | entropy_loss | -5.2 | | explained_variance | 0.982 | | learning_rate | 0.000238 | | loss | -0.027 | | n_updates | 2432 | | policy_gradient_loss | -0.0199 | | value_loss | 0.000185 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 49.6 | | ep_rew_mean | 0.844 | | time/ | | | fps | 1126 | | iterations | 610 | | time_elapsed | 4434 | | total_timesteps | 4997120 | | train/ | | | approx_kl | 0.054123774 | | clip_fraction | 0.294 | | clip_range | 0.144 | | entropy_loss | -5.17 | | explained_variance | 0.962 | | learning_rate | 0.000238 | | loss | -0.0266 | | n_updates | 2436 | | policy_gradient_loss | -0.0171 | | value_loss | 0.00031 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 48.3 | | ep_rew_mean | 0.841 | | time/ | | | fps | 1126 | | iterations | 611 | | time_elapsed | 4441 | | total_timesteps | 5005312 | | train/ | | | approx_kl | 0.051901914 | | clip_fraction | 0.299 | | clip_range | 0.144 | | entropy_loss | -5.27 | | explained_variance | 0.95 | | learning_rate | 0.000238 | | loss | -0.0218 | | n_updates | 2440 | | policy_gradient_loss | -0.023 | | value_loss | 0.000555 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 48.4 | | ep_rew_mean | 0.848 | | time/ | | | fps | 1126 | | iterations | 612 | | time_elapsed | 4448 | | total_timesteps | 5013504 | | train/ | | | approx_kl | 0.032188684 | | clip_fraction | 0.262 | | clip_range | 0.144 | | entropy_loss | -5.07 | | explained_variance | 0.973 | | learning_rate | 0.000238 | | loss | -0.0202 | | n_updates | 2444 | | policy_gradient_loss | -0.0151 | | value_loss | 0.000219 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 48.8 | | ep_rew_mean | 0.848 | | time/ | | | fps | 1126 | | iterations | 613 | | time_elapsed | 4456 | | total_timesteps | 5021696 | | train/ | | | approx_kl | 0.030742245 | | clip_fraction | 0.28 | | clip_range | 0.144 | | entropy_loss | -4.98 | | explained_variance | 0.936 | | learning_rate | 0.000238 | | loss | -0.0166 | | n_updates | 2448 | | policy_gradient_loss | -0.0107 | | value_loss | 0.000463 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 46.8 | | ep_rew_mean | 0.852 | | time/ | | | fps | 1126 | | iterations | 614 | | time_elapsed | 4463 | | total_timesteps | 5029888 | | train/ | | | approx_kl | 0.026955975 | | clip_fraction | 0.235 | | clip_range | 0.144 | | entropy_loss | -4.96 | | explained_variance | 0.979 | | learning_rate | 0.000238 | | loss | -0.0163 | | n_updates | 2452 | | policy_gradient_loss | -0.00907 | | value_loss | 0.000129 | ----------------------------------------- --------------------------------------- | rollout/ | | | ep_len_mean | 50.1 | | ep_rew_mean | 0.844 | | time/ | | | fps | 1126 | | iterations | 615 | | time_elapsed | 4470 | | total_timesteps | 5038080 | | train/ | | | approx_kl | 0.0319663 | | clip_fraction | 0.257 | | clip_range | 0.144 | | entropy_loss | -4.99 | | explained_variance | 0.964 | | learning_rate | 0.000238 | | loss | -0.0193 | | n_updates | 2456 | | policy_gradient_loss | -0.0116 | | value_loss | 0.000231 | --------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 47.6 | | ep_rew_mean | 0.851 | | time/ | | | fps | 1126 | | iterations | 616 | | time_elapsed | 4478 | | total_timesteps | 5046272 | | train/ | | | approx_kl | 0.042172626 | | clip_fraction | 0.267 | | clip_range | 0.144 | | entropy_loss | -5.12 | | explained_variance | 0.935 | | learning_rate | 0.000238 | | loss | -0.0227 | | n_updates | 2460 | | policy_gradient_loss | -0.0169 | | value_loss | 0.000548 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 48.8 | | ep_rew_mean | 0.849 | | time/ | | | fps | 1126 | | iterations | 617 | | time_elapsed | 4485 | | total_timesteps | 5054464 | | train/ | | | approx_kl | 0.031552512 | | clip_fraction | 0.257 | | clip_range | 0.144 | | entropy_loss | -5.08 | | explained_variance | 0.948 | | learning_rate | 0.000238 | | loss | -0.013 | | n_updates | 2464 | | policy_gradient_loss | -0.0135 | | value_loss | 0.000374 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 48.6 | | ep_rew_mean | 0.848 | | time/ | | | fps | 1126 | | iterations | 618 | | time_elapsed | 4492 | | total_timesteps | 5062656 | | train/ | | | approx_kl | 0.039125167 | | clip_fraction | 0.23 | | clip_range | 0.144 | | entropy_loss | -5.12 | | explained_variance | 0.956 | | learning_rate | 0.000237 | | loss | -0.0163 | | n_updates | 2468 | | policy_gradient_loss | -0.0162 | | value_loss | 0.000389 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 46 | | ep_rew_mean | 0.853 | | time/ | | | fps | 1126 | | iterations | 619 | | time_elapsed | 4500 | | total_timesteps | 5070848 | | train/ | | | approx_kl | 0.041809745 | | clip_fraction | 0.256 | | clip_range | 0.144 | | entropy_loss | -5.05 | | explained_variance | 0.957 | | learning_rate | 0.000237 | | loss | -0.0208 | | n_updates | 2472 | | policy_gradient_loss | -0.0144 | | value_loss | 0.000287 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 50.5 | | ep_rew_mean | 0.846 | | time/ | | | fps | 1126 | | iterations | 620 | | time_elapsed | 4507 | | total_timesteps | 5079040 | | train/ | | | approx_kl | 0.027817583 | | clip_fraction | 0.224 | | clip_range | 0.144 | | entropy_loss | -4.99 | | explained_variance | 0.967 | | learning_rate | 0.000237 | | loss | -0.00911 | | n_updates | 2476 | | policy_gradient_loss | -0.00608 | | value_loss | 0.000198 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 48.9 | | ep_rew_mean | 0.847 | | time/ | | | fps | 1126 | | iterations | 621 | | time_elapsed | 4514 | | total_timesteps | 5087232 | | train/ | | | approx_kl | 0.04878187 | | clip_fraction | 0.266 | | clip_range | 0.144 | | entropy_loss | -5.19 | | explained_variance | 0.95 | | learning_rate | 0.000237 | | loss | -0.0333 | | n_updates | 2480 | | policy_gradient_loss | -0.02 | | value_loss | 0.000452 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 49.8 | | ep_rew_mean | 0.843 | | time/ | | | fps | 1126 | | iterations | 622 | | time_elapsed | 4521 | | total_timesteps | 5095424 | | train/ | | | approx_kl | 0.046289247 | | clip_fraction | 0.267 | | clip_range | 0.144 | | entropy_loss | -5.13 | | explained_variance | 0.964 | | learning_rate | 0.000237 | | loss | -0.0208 | | n_updates | 2484 | | policy_gradient_loss | -0.0147 | | value_loss | 0.000279 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 48.5 | | ep_rew_mean | 0.848 | | time/ | | | fps | 1126 | | iterations | 623 | | time_elapsed | 4529 | | total_timesteps | 5103616 | | train/ | | | approx_kl | 0.036489025 | | clip_fraction | 0.253 | | clip_range | 0.144 | | entropy_loss | -5.11 | | explained_variance | 0.979 | | learning_rate | 0.000237 | | loss | -0.0207 | | n_updates | 2488 | | policy_gradient_loss | -0.0172 | | value_loss | 0.000185 | ----------------------------------------- --------------------------------------- | rollout/ | | | ep_len_mean | 47.8 | | ep_rew_mean | 0.852 | | time/ | | | fps | 1126 | | iterations | 624 | | time_elapsed | 4536 | | total_timesteps | 5111808 | | train/ | | | approx_kl | 0.0396738 | | clip_fraction | 0.273 | | clip_range | 0.144 | | entropy_loss | -4.99 | | explained_variance | 0.983 | | learning_rate | 0.000237 | | loss | -0.0138 | | n_updates | 2492 | | policy_gradient_loss | -0.0115 | | value_loss | 0.000132 | --------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 47.3 | | ep_rew_mean | 0.851 | | time/ | | | fps | 1126 | | iterations | 625 | | time_elapsed | 4543 | | total_timesteps | 5120000 | | train/ | | | approx_kl | 0.039055005 | | clip_fraction | 0.291 | | clip_range | 0.144 | | entropy_loss | -5.1 | | explained_variance | 0.961 | | learning_rate | 0.000237 | | loss | -0.0195 | | n_updates | 2496 | | policy_gradient_loss | -0.0155 | | value_loss | 0.000308 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 49.2 | | ep_rew_mean | 0.846 | | time/ | | | fps | 1126 | | iterations | 626 | | time_elapsed | 4551 | | total_timesteps | 5128192 | | train/ | | | approx_kl | 0.022153018 | | clip_fraction | 0.232 | | clip_range | 0.144 | | entropy_loss | -5.05 | | explained_variance | 0.961 | | learning_rate | 0.000237 | | loss | -0.0146 | | n_updates | 2500 | | policy_gradient_loss | -0.00889 | | value_loss | 0.000243 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 47 | | ep_rew_mean | 0.852 | | time/ | | | fps | 1126 | | iterations | 627 | | time_elapsed | 4558 | | total_timesteps | 5136384 | | train/ | | | approx_kl | 0.040569253 | | clip_fraction | 0.249 | | clip_range | 0.144 | | entropy_loss | -5.12 | | explained_variance | 0.951 | | learning_rate | 0.000237 | | loss | -0.021 | | n_updates | 2504 | | policy_gradient_loss | -0.0163 | | value_loss | 0.000386 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 46 | | ep_rew_mean | 0.853 | | time/ | | | fps | 1126 | | iterations | 628 | | time_elapsed | 4565 | | total_timesteps | 5144576 | | train/ | | | approx_kl | 0.034480445 | | clip_fraction | 0.2 | | clip_range | 0.144 | | entropy_loss | -5.08 | | explained_variance | 0.963 | | learning_rate | 0.000237 | | loss | -0.0242 | | n_updates | 2508 | | policy_gradient_loss | -0.0128 | | value_loss | 0.000233 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 49.1 | | ep_rew_mean | 0.846 | | time/ | | | fps | 1126 | | iterations | 629 | | time_elapsed | 4573 | | total_timesteps | 5152768 | | train/ | | | approx_kl | 0.028778546 | | clip_fraction | 0.237 | | clip_range | 0.144 | | entropy_loss | -5.08 | | explained_variance | 0.97 | | learning_rate | 0.000237 | | loss | -0.0204 | | n_updates | 2512 | | policy_gradient_loss | -0.0103 | | value_loss | 0.00022 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 50.5 | | ep_rew_mean | 0.838 | | time/ | | | fps | 1126 | | iterations | 630 | | time_elapsed | 4580 | | total_timesteps | 5160960 | | train/ | | | approx_kl | 0.037687283 | | clip_fraction | 0.257 | | clip_range | 0.144 | | entropy_loss | -5.15 | | explained_variance | 0.959 | | learning_rate | 0.000237 | | loss | -0.0272 | | n_updates | 2516 | | policy_gradient_loss | -0.0168 | | value_loss | 0.000318 | ----------------------------------------- -------------------------------------- | rollout/ | | | ep_len_mean | 48.9 | | ep_rew_mean | 0.847 | | time/ | | | fps | 1126 | | iterations | 631 | | time_elapsed | 4587 | | total_timesteps | 5169152 | | train/ | | | approx_kl | 0.048883 | | clip_fraction | 0.304 | | clip_range | 0.144 | | entropy_loss | -5.19 | | explained_variance | 0.948 | | learning_rate | 0.000237 | | loss | -0.0232 | | n_updates | 2520 | | policy_gradient_loss | -0.0178 | | value_loss | 0.00049 | -------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 48.1 | | ep_rew_mean | 0.847 | | time/ | | | fps | 1126 | | iterations | 632 | | time_elapsed | 4594 | | total_timesteps | 5177344 | | train/ | | | approx_kl | 0.09981434 | | clip_fraction | 0.235 | | clip_range | 0.144 | | entropy_loss | -5.17 | | explained_variance | 0.957 | | learning_rate | 0.000237 | | loss | -0.0219 | | n_updates | 2524 | | policy_gradient_loss | -0.014 | | value_loss | 0.000315 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 46.2 | | ep_rew_mean | 0.854 | | time/ | | | fps | 1126 | | iterations | 633 | | time_elapsed | 4602 | | total_timesteps | 5185536 | | train/ | | | approx_kl | 0.043999217 | | clip_fraction | 0.269 | | clip_range | 0.144 | | entropy_loss | -5.15 | | explained_variance | 0.957 | | learning_rate | 0.000237 | | loss | -0.0212 | | n_updates | 2528 | | policy_gradient_loss | -0.0177 | | value_loss | 0.000324 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 54.9 | | ep_rew_mean | 0.835 | | time/ | | | fps | 1126 | | iterations | 634 | | time_elapsed | 4609 | | total_timesteps | 5193728 | | train/ | | | approx_kl | 0.032066435 | | clip_fraction | 0.252 | | clip_range | 0.144 | | entropy_loss | -5.15 | | explained_variance | 0.963 | | learning_rate | 0.000237 | | loss | -0.023 | | n_updates | 2532 | | policy_gradient_loss | -0.0158 | | value_loss | 0.000279 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 50.6 | | ep_rew_mean | 0.844 | | time/ | | | fps | 1126 | | iterations | 635 | | time_elapsed | 4616 | | total_timesteps | 5201920 | | train/ | | | approx_kl | 0.053254317 | | clip_fraction | 0.29 | | clip_range | 0.144 | | entropy_loss | -5.36 | | explained_variance | 0.952 | | learning_rate | 0.000237 | | loss | -0.0275 | | n_updates | 2536 | | policy_gradient_loss | -0.0207 | | value_loss | 0.000535 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 49.6 | | ep_rew_mean | 0.841 | | time/ | | | fps | 1126 | | iterations | 636 | | time_elapsed | 4624 | | total_timesteps | 5210112 | | train/ | | | approx_kl | 0.041626655 | | clip_fraction | 0.236 | | clip_range | 0.143 | | entropy_loss | -5.26 | | explained_variance | 0.938 | | learning_rate | 0.000237 | | loss | -0.0182 | | n_updates | 2540 | | policy_gradient_loss | -0.0176 | | value_loss | 0.000477 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 50.9 | | ep_rew_mean | 0.84 | | time/ | | | fps | 1126 | | iterations | 637 | | time_elapsed | 4631 | | total_timesteps | 5218304 | | train/ | | | approx_kl | 0.046436526 | | clip_fraction | 0.292 | | clip_range | 0.143 | | entropy_loss | -5.29 | | explained_variance | 0.94 | | learning_rate | 0.000237 | | loss | -0.0264 | | n_updates | 2544 | | policy_gradient_loss | -0.0203 | | value_loss | 0.000573 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 50.9 | | ep_rew_mean | 0.841 | | time/ | | | fps | 1126 | | iterations | 638 | | time_elapsed | 4639 | | total_timesteps | 5226496 | | train/ | | | approx_kl | 0.04340884 | | clip_fraction | 0.258 | | clip_range | 0.143 | | entropy_loss | -5.23 | | explained_variance | 0.954 | | learning_rate | 0.000237 | | loss | -0.024 | | n_updates | 2548 | | policy_gradient_loss | -0.0176 | | value_loss | 0.000389 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 51.1 | | ep_rew_mean | 0.844 | | time/ | | | fps | 1126 | | iterations | 639 | | time_elapsed | 4646 | | total_timesteps | 5234688 | | train/ | | | approx_kl | 0.06817353 | | clip_fraction | 0.261 | | clip_range | 0.143 | | entropy_loss | -5.22 | | explained_variance | 0.971 | | learning_rate | 0.000237 | | loss | -0.0248 | | n_updates | 2552 | | policy_gradient_loss | -0.016 | | value_loss | 0.000242 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 47.2 | | ep_rew_mean | 0.845 | | time/ | | | fps | 1126 | | iterations | 640 | | time_elapsed | 4653 | | total_timesteps | 5242880 | | train/ | | | approx_kl | 0.04421519 | | clip_fraction | 0.268 | | clip_range | 0.143 | | entropy_loss | -5.2 | | explained_variance | 0.947 | | learning_rate | 0.000237 | | loss | -0.0175 | | n_updates | 2556 | | policy_gradient_loss | -0.0172 | | value_loss | 0.000411 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 47.7 | | ep_rew_mean | 0.852 | | time/ | | | fps | 1126 | | iterations | 641 | | time_elapsed | 4660 | | total_timesteps | 5251072 | | train/ | | | approx_kl | 0.04762256 | | clip_fraction | 0.26 | | clip_range | 0.143 | | entropy_loss | -5.1 | | explained_variance | 0.972 | | learning_rate | 0.000237 | | loss | -0.0187 | | n_updates | 2560 | | policy_gradient_loss | -0.0143 | | value_loss | 0.000225 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 48.4 | | ep_rew_mean | 0.849 | | time/ | | | fps | 1126 | | iterations | 642 | | time_elapsed | 4668 | | total_timesteps | 5259264 | | train/ | | | approx_kl | 0.049721286 | | clip_fraction | 0.264 | | clip_range | 0.143 | | entropy_loss | -5.05 | | explained_variance | 0.906 | | learning_rate | 0.000237 | | loss | -0.0249 | | n_updates | 2564 | | policy_gradient_loss | -0.0144 | | value_loss | 0.000677 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 50.5 | | ep_rew_mean | 0.833 | | time/ | | | fps | 1126 | | iterations | 643 | | time_elapsed | 4675 | | total_timesteps | 5267456 | | train/ | | | approx_kl | 0.034132294 | | clip_fraction | 0.276 | | clip_range | 0.143 | | entropy_loss | -5.09 | | explained_variance | 0.957 | | learning_rate | 0.000237 | | loss | -0.0148 | | n_updates | 2568 | | policy_gradient_loss | -0.0144 | | value_loss | 0.000363 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 47.8 | | ep_rew_mean | 0.848 | | time/ | | | fps | 1126 | | iterations | 644 | | time_elapsed | 4682 | | total_timesteps | 5275648 | | train/ | | | approx_kl | 0.053728428 | | clip_fraction | 0.287 | | clip_range | 0.143 | | entropy_loss | -5.09 | | explained_variance | 0.964 | | learning_rate | 0.000237 | | loss | -0.0148 | | n_updates | 2572 | | policy_gradient_loss | -0.0174 | | value_loss | 0.000358 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 46.5 | | ep_rew_mean | 0.853 | | time/ | | | fps | 1126 | | iterations | 645 | | time_elapsed | 4690 | | total_timesteps | 5283840 | | train/ | | | approx_kl | 0.058327414 | | clip_fraction | 0.288 | | clip_range | 0.143 | | entropy_loss | -5.08 | | explained_variance | 0.966 | | learning_rate | 0.000237 | | loss | -0.0228 | | n_updates | 2576 | | policy_gradient_loss | -0.0194 | | value_loss | 0.000318 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 48.3 | | ep_rew_mean | 0.842 | | time/ | | | fps | 1126 | | iterations | 646 | | time_elapsed | 4697 | | total_timesteps | 5292032 | | train/ | | | approx_kl | 0.03609147 | | clip_fraction | 0.263 | | clip_range | 0.143 | | entropy_loss | -4.93 | | explained_variance | 0.955 | | learning_rate | 0.000237 | | loss | -0.0156 | | n_updates | 2580 | | policy_gradient_loss | -0.0118 | | value_loss | 0.000303 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 47.4 | | ep_rew_mean | 0.843 | | time/ | | | fps | 1126 | | iterations | 647 | | time_elapsed | 4704 | | total_timesteps | 5300224 | | train/ | | | approx_kl | 0.03956795 | | clip_fraction | 0.27 | | clip_range | 0.143 | | entropy_loss | -4.95 | | explained_variance | 0.96 | | learning_rate | 0.000237 | | loss | -0.0267 | | n_updates | 2584 | | policy_gradient_loss | -0.0125 | | value_loss | 0.00032 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 49.8 | | ep_rew_mean | 0.84 | | time/ | | | fps | 1126 | | iterations | 648 | | time_elapsed | 4711 | | total_timesteps | 5308416 | | train/ | | | approx_kl | 0.040171698 | | clip_fraction | 0.23 | | clip_range | 0.143 | | entropy_loss | -4.94 | | explained_variance | 0.972 | | learning_rate | 0.000237 | | loss | -0.0236 | | n_updates | 2588 | | policy_gradient_loss | -0.0122 | | value_loss | 0.000181 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 47.7 | | ep_rew_mean | 0.847 | | time/ | | | fps | 1126 | | iterations | 649 | | time_elapsed | 4719 | | total_timesteps | 5316608 | | train/ | | | approx_kl | 0.042866707 | | clip_fraction | 0.291 | | clip_range | 0.143 | | entropy_loss | -4.99 | | explained_variance | 0.956 | | learning_rate | 0.000237 | | loss | -0.0196 | | n_updates | 2592 | | policy_gradient_loss | -0.0155 | | value_loss | 0.000375 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 46.5 | | ep_rew_mean | 0.854 | | time/ | | | fps | 1126 | | iterations | 650 | | time_elapsed | 4726 | | total_timesteps | 5324800 | | train/ | | | approx_kl | 0.04987514 | | clip_fraction | 0.256 | | clip_range | 0.143 | | entropy_loss | -5.01 | | explained_variance | 0.972 | | learning_rate | 0.000237 | | loss | -0.0247 | | n_updates | 2596 | | policy_gradient_loss | -0.0173 | | value_loss | 0.000194 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 47.1 | | ep_rew_mean | 0.851 | | time/ | | | fps | 1126 | | iterations | 651 | | time_elapsed | 4733 | | total_timesteps | 5332992 | | train/ | | | approx_kl | 0.033198718 | | clip_fraction | 0.278 | | clip_range | 0.143 | | entropy_loss | -4.98 | | explained_variance | 0.956 | | learning_rate | 0.000237 | | loss | -0.017 | | n_updates | 2600 | | policy_gradient_loss | -0.013 | | value_loss | 0.000307 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 51.1 | | ep_rew_mean | 0.834 | | time/ | | | fps | 1126 | | iterations | 652 | | time_elapsed | 4740 | | total_timesteps | 5341184 | | train/ | | | approx_kl | 0.04095178 | | clip_fraction | 0.225 | | clip_range | 0.143 | | entropy_loss | -4.97 | | explained_variance | 0.955 | | learning_rate | 0.000237 | | loss | -0.0154 | | n_updates | 2604 | | policy_gradient_loss | -0.0112 | | value_loss | 0.000273 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 51.4 | | ep_rew_mean | 0.836 | | time/ | | | fps | 1126 | | iterations | 653 | | time_elapsed | 4747 | | total_timesteps | 5349376 | | train/ | | | approx_kl | 0.049831104 | | clip_fraction | 0.274 | | clip_range | 0.143 | | entropy_loss | -5.1 | | explained_variance | 0.968 | | learning_rate | 0.000237 | | loss | -0.0211 | | n_updates | 2608 | | policy_gradient_loss | -0.0199 | | value_loss | 0.000303 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 48.7 | | ep_rew_mean | 0.84 | | time/ | | | fps | 1126 | | iterations | 654 | | time_elapsed | 4754 | | total_timesteps | 5357568 | | train/ | | | approx_kl | 0.058760896 | | clip_fraction | 0.318 | | clip_range | 0.143 | | entropy_loss | -5.09 | | explained_variance | 0.954 | | learning_rate | 0.000237 | | loss | -0.0282 | | n_updates | 2612 | | policy_gradient_loss | -0.0198 | | value_loss | 0.000543 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 48.4 | | ep_rew_mean | 0.849 | | time/ | | | fps | 1126 | | iterations | 655 | | time_elapsed | 4762 | | total_timesteps | 5365760 | | train/ | | | approx_kl | 0.033480577 | | clip_fraction | 0.278 | | clip_range | 0.143 | | entropy_loss | -5.06 | | explained_variance | 0.972 | | learning_rate | 0.000237 | | loss | -0.0184 | | n_updates | 2616 | | policy_gradient_loss | -0.0155 | | value_loss | 0.000226 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 48.5 | | ep_rew_mean | 0.848 | | time/ | | | fps | 1126 | | iterations | 656 | | time_elapsed | 4769 | | total_timesteps | 5373952 | | train/ | | | approx_kl | 0.042696614 | | clip_fraction | 0.27 | | clip_range | 0.143 | | entropy_loss | -5.11 | | explained_variance | 0.976 | | learning_rate | 0.000237 | | loss | -0.0274 | | n_updates | 2620 | | policy_gradient_loss | -0.0191 | | value_loss | 0.000216 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 47.2 | | ep_rew_mean | 0.851 | | time/ | | | fps | 1126 | | iterations | 657 | | time_elapsed | 4776 | | total_timesteps | 5382144 | | train/ | | | approx_kl | 0.04923485 | | clip_fraction | 0.247 | | clip_range | 0.143 | | entropy_loss | -5.13 | | explained_variance | 0.986 | | learning_rate | 0.000237 | | loss | -0.0273 | | n_updates | 2624 | | policy_gradient_loss | -0.018 | | value_loss | 0.000125 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 49.2 | | ep_rew_mean | 0.844 | | time/ | | | fps | 1126 | | iterations | 658 | | time_elapsed | 4784 | | total_timesteps | 5390336 | | train/ | | | approx_kl | 0.04555118 | | clip_fraction | 0.277 | | clip_range | 0.143 | | entropy_loss | -5.04 | | explained_variance | 0.962 | | learning_rate | 0.000237 | | loss | -0.0154 | | n_updates | 2628 | | policy_gradient_loss | -0.0129 | | value_loss | 0.000273 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 46 | | ep_rew_mean | 0.853 | | time/ | | | fps | 1126 | | iterations | 659 | | time_elapsed | 4791 | | total_timesteps | 5398528 | | train/ | | | approx_kl | 0.08245316 | | clip_fraction | 0.284 | | clip_range | 0.143 | | entropy_loss | -5.13 | | explained_variance | 0.968 | | learning_rate | 0.000237 | | loss | -0.0313 | | n_updates | 2632 | | policy_gradient_loss | -0.0211 | | value_loss | 0.000336 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 50.1 | | ep_rew_mean | 0.843 | | time/ | | | fps | 1126 | | iterations | 660 | | time_elapsed | 4798 | | total_timesteps | 5406720 | | train/ | | | approx_kl | 0.025834586 | | clip_fraction | 0.198 | | clip_range | 0.143 | | entropy_loss | -5.04 | | explained_variance | 0.993 | | learning_rate | 0.000237 | | loss | -0.0229 | | n_updates | 2636 | | policy_gradient_loss | -0.00875 | | value_loss | 5.84e-05 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 46.2 | | ep_rew_mean | 0.854 | | time/ | | | fps | 1126 | | iterations | 661 | | time_elapsed | 4806 | | total_timesteps | 5414912 | | train/ | | | approx_kl | 0.049504377 | | clip_fraction | 0.294 | | clip_range | 0.143 | | entropy_loss | -5.12 | | explained_variance | 0.975 | | learning_rate | 0.000237 | | loss | -0.0285 | | n_updates | 2640 | | policy_gradient_loss | -0.0167 | | value_loss | 0.000229 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 49 | | ep_rew_mean | 0.84 | | time/ | | | fps | 1126 | | iterations | 662 | | time_elapsed | 4813 | | total_timesteps | 5423104 | | train/ | | | approx_kl | 0.039111726 | | clip_fraction | 0.223 | | clip_range | 0.143 | | entropy_loss | -5.02 | | explained_variance | 0.979 | | learning_rate | 0.000237 | | loss | -0.0237 | | n_updates | 2644 | | policy_gradient_loss | -0.00971 | | value_loss | 0.000125 | ----------------------------------------- --------------------------------------- | rollout/ | | | ep_len_mean | 49 | | ep_rew_mean | 0.842 | | time/ | | | fps | 1126 | | iterations | 663 | | time_elapsed | 4820 | | total_timesteps | 5431296 | | train/ | | | approx_kl | 0.0505772 | | clip_fraction | 0.313 | | clip_range | 0.143 | | entropy_loss | -5.13 | | explained_variance | 0.972 | | learning_rate | 0.000237 | | loss | -0.032 | | n_updates | 2648 | | policy_gradient_loss | -0.019 | | value_loss | 0.000287 | --------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 50.1 | | ep_rew_mean | 0.841 | | time/ | | | fps | 1126 | | iterations | 664 | | time_elapsed | 4828 | | total_timesteps | 5439488 | | train/ | | | approx_kl | 0.04492996 | | clip_fraction | 0.265 | | clip_range | 0.143 | | entropy_loss | -5.04 | | explained_variance | 0.963 | | learning_rate | 0.000237 | | loss | -0.0204 | | n_updates | 2652 | | policy_gradient_loss | -0.0139 | | value_loss | 0.000284 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 47.9 | | ep_rew_mean | 0.847 | | time/ | | | fps | 1126 | | iterations | 665 | | time_elapsed | 4835 | | total_timesteps | 5447680 | | train/ | | | approx_kl | 0.06896451 | | clip_fraction | 0.288 | | clip_range | 0.143 | | entropy_loss | -5.11 | | explained_variance | 0.973 | | learning_rate | 0.000237 | | loss | -0.0346 | | n_updates | 2656 | | policy_gradient_loss | -0.0194 | | value_loss | 0.000288 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 46.6 | | ep_rew_mean | 0.853 | | time/ | | | fps | 1126 | | iterations | 666 | | time_elapsed | 4842 | | total_timesteps | 5455872 | | train/ | | | approx_kl | 0.03433504 | | clip_fraction | 0.261 | | clip_range | 0.143 | | entropy_loss | -5.05 | | explained_variance | 0.971 | | learning_rate | 0.000237 | | loss | -0.022 | | n_updates | 2660 | | policy_gradient_loss | -0.0143 | | value_loss | 0.000239 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 46.8 | | ep_rew_mean | 0.853 | | time/ | | | fps | 1126 | | iterations | 667 | | time_elapsed | 4850 | | total_timesteps | 5464064 | | train/ | | | approx_kl | 0.04043471 | | clip_fraction | 0.26 | | clip_range | 0.143 | | entropy_loss | -5 | | explained_variance | 0.947 | | learning_rate | 0.000236 | | loss | -0.0167 | | n_updates | 2664 | | policy_gradient_loss | -0.0108 | | value_loss | 0.000285 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 47.9 | | ep_rew_mean | 0.849 | | time/ | | | fps | 1126 | | iterations | 668 | | time_elapsed | 4857 | | total_timesteps | 5472256 | | train/ | | | approx_kl | 0.02984986 | | clip_fraction | 0.242 | | clip_range | 0.143 | | entropy_loss | -4.99 | | explained_variance | 0.952 | | learning_rate | 0.000236 | | loss | -0.00662 | | n_updates | 2668 | | policy_gradient_loss | -0.00949 | | value_loss | 0.000294 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 50.3 | | ep_rew_mean | 0.845 | | time/ | | | fps | 1126 | | iterations | 669 | | time_elapsed | 4864 | | total_timesteps | 5480448 | | train/ | | | approx_kl | 0.030380346 | | clip_fraction | 0.263 | | clip_range | 0.143 | | entropy_loss | -5.04 | | explained_variance | 0.943 | | learning_rate | 0.000236 | | loss | -0.0198 | | n_updates | 2672 | | policy_gradient_loss | -0.0138 | | value_loss | 0.000402 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 46.7 | | ep_rew_mean | 0.845 | | time/ | | | fps | 1126 | | iterations | 670 | | time_elapsed | 4872 | | total_timesteps | 5488640 | | train/ | | | approx_kl | 0.06422448 | | clip_fraction | 0.241 | | clip_range | 0.143 | | entropy_loss | -5.05 | | explained_variance | 0.975 | | learning_rate | 0.000236 | | loss | -0.026 | | n_updates | 2676 | | policy_gradient_loss | -0.02 | | value_loss | 0.000204 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 48.3 | | ep_rew_mean | 0.845 | | time/ | | | fps | 1126 | | iterations | 671 | | time_elapsed | 4879 | | total_timesteps | 5496832 | | train/ | | | approx_kl | 0.023435526 | | clip_fraction | 0.23 | | clip_range | 0.143 | | entropy_loss | -4.92 | | explained_variance | 0.989 | | learning_rate | 0.000236 | | loss | -0.00982 | | n_updates | 2680 | | policy_gradient_loss | -0.00685 | | value_loss | 9.02e-05 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 46.6 | | ep_rew_mean | 0.855 | | time/ | | | fps | 1126 | | iterations | 672 | | time_elapsed | 4886 | | total_timesteps | 5505024 | | train/ | | | approx_kl | 0.05860194 | | clip_fraction | 0.26 | | clip_range | 0.143 | | entropy_loss | -4.94 | | explained_variance | 0.97 | | learning_rate | 0.000236 | | loss | -0.019 | | n_updates | 2684 | | policy_gradient_loss | -0.0127 | | value_loss | 0.00021 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 46 | | ep_rew_mean | 0.853 | | time/ | | | fps | 1126 | | iterations | 673 | | time_elapsed | 4894 | | total_timesteps | 5513216 | | train/ | | | approx_kl | 0.03285363 | | clip_fraction | 0.238 | | clip_range | 0.143 | | entropy_loss | -4.92 | | explained_variance | 0.96 | | learning_rate | 0.000236 | | loss | -0.0125 | | n_updates | 2688 | | policy_gradient_loss | -0.0103 | | value_loss | 0.000276 | ---------------------------------------- --------------------------------------- | rollout/ | | | ep_len_mean | 49.5 | | ep_rew_mean | 0.845 | | time/ | | | fps | 1126 | | iterations | 674 | | time_elapsed | 4901 | | total_timesteps | 5521408 | | train/ | | | approx_kl | 0.0384774 | | clip_fraction | 0.207 | | clip_range | 0.143 | | entropy_loss | -4.95 | | explained_variance | 0.974 | | learning_rate | 0.000236 | | loss | -0.0173 | | n_updates | 2692 | | policy_gradient_loss | -0.00955 | | value_loss | 0.000156 | --------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 48 | | ep_rew_mean | 0.848 | | time/ | | | fps | 1126 | | iterations | 675 | | time_elapsed | 4909 | | total_timesteps | 5529600 | | train/ | | | approx_kl | 0.044978946 | | clip_fraction | 0.281 | | clip_range | 0.143 | | entropy_loss | -5.17 | | explained_variance | 0.956 | | learning_rate | 0.000236 | | loss | -0.0329 | | n_updates | 2696 | | policy_gradient_loss | -0.0214 | | value_loss | 0.000395 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 48 | | ep_rew_mean | 0.848 | | time/ | | | fps | 1126 | | iterations | 676 | | time_elapsed | 4916 | | total_timesteps | 5537792 | | train/ | | | approx_kl | 0.044992045 | | clip_fraction | 0.246 | | clip_range | 0.143 | | entropy_loss | -5.1 | | explained_variance | 0.976 | | learning_rate | 0.000236 | | loss | -0.0221 | | n_updates | 2700 | | policy_gradient_loss | -0.0171 | | value_loss | 0.000188 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 47.8 | | ep_rew_mean | 0.847 | | time/ | | | fps | 1126 | | iterations | 677 | | time_elapsed | 4923 | | total_timesteps | 5545984 | | train/ | | | approx_kl | 0.045260586 | | clip_fraction | 0.185 | | clip_range | 0.143 | | entropy_loss | -5.06 | | explained_variance | 0.99 | | learning_rate | 0.000236 | | loss | -0.022 | | n_updates | 2704 | | policy_gradient_loss | -0.0144 | | value_loss | 7.56e-05 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 46.2 | | ep_rew_mean | 0.854 | | time/ | | | fps | 1126 | | iterations | 678 | | time_elapsed | 4930 | | total_timesteps | 5554176 | | train/ | | | approx_kl | 0.031672657 | | clip_fraction | 0.282 | | clip_range | 0.143 | | entropy_loss | -5.05 | | explained_variance | 0.957 | | learning_rate | 0.000236 | | loss | -0.0145 | | n_updates | 2708 | | policy_gradient_loss | -0.0149 | | value_loss | 0.000319 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 48.2 | | ep_rew_mean | 0.847 | | time/ | | | fps | 1126 | | iterations | 679 | | time_elapsed | 4937 | | total_timesteps | 5562368 | | train/ | | | approx_kl | 0.012920519 | | clip_fraction | 0.238 | | clip_range | 0.143 | | entropy_loss | -4.96 | | explained_variance | 0.971 | | learning_rate | 0.000236 | | loss | -0.0019 | | n_updates | 2712 | | policy_gradient_loss | -0.00681 | | value_loss | 0.000175 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 47.2 | | ep_rew_mean | 0.851 | | time/ | | | fps | 1126 | | iterations | 680 | | time_elapsed | 4945 | | total_timesteps | 5570560 | | train/ | | | approx_kl | 0.05727388 | | clip_fraction | 0.227 | | clip_range | 0.143 | | entropy_loss | -5.09 | | explained_variance | 0.948 | | learning_rate | 0.000236 | | loss | -0.0196 | | n_updates | 2716 | | policy_gradient_loss | -0.0149 | | value_loss | 0.000329 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 50.9 | | ep_rew_mean | 0.842 | | time/ | | | fps | 1126 | | iterations | 681 | | time_elapsed | 4952 | | total_timesteps | 5578752 | | train/ | | | approx_kl | 0.05344817 | | clip_fraction | 0.212 | | clip_range | 0.143 | | entropy_loss | -5.16 | | explained_variance | 0.976 | | learning_rate | 0.000236 | | loss | -0.0232 | | n_updates | 2720 | | policy_gradient_loss | -0.0165 | | value_loss | 0.000174 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 50.8 | | ep_rew_mean | 0.843 | | time/ | | | fps | 1126 | | iterations | 682 | | time_elapsed | 4959 | | total_timesteps | 5586944 | | train/ | | | approx_kl | 0.046642303 | | clip_fraction | 0.281 | | clip_range | 0.143 | | entropy_loss | -5.14 | | explained_variance | 0.959 | | learning_rate | 0.000236 | | loss | -0.0293 | | n_updates | 2724 | | policy_gradient_loss | -0.0211 | | value_loss | 0.000376 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 46.8 | | ep_rew_mean | 0.852 | | time/ | | | fps | 1126 | | iterations | 683 | | time_elapsed | 4967 | | total_timesteps | 5595136 | | train/ | | | approx_kl | 0.059482977 | | clip_fraction | 0.23 | | clip_range | 0.143 | | entropy_loss | -5.13 | | explained_variance | 0.956 | | learning_rate | 0.000236 | | loss | -0.0291 | | n_updates | 2728 | | policy_gradient_loss | -0.0186 | | value_loss | 0.000353 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 46.4 | | ep_rew_mean | 0.854 | | time/ | | | fps | 1126 | | iterations | 684 | | time_elapsed | 4974 | | total_timesteps | 5603328 | | train/ | | | approx_kl | 0.028259914 | | clip_fraction | 0.203 | | clip_range | 0.143 | | entropy_loss | -4.98 | | explained_variance | 0.978 | | learning_rate | 0.000236 | | loss | -0.0137 | | n_updates | 2732 | | policy_gradient_loss | -0.00825 | | value_loss | 0.000117 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 46.2 | | ep_rew_mean | 0.854 | | time/ | | | fps | 1126 | | iterations | 685 | | time_elapsed | 4981 | | total_timesteps | 5611520 | | train/ | | | approx_kl | 0.02907198 | | clip_fraction | 0.225 | | clip_range | 0.143 | | entropy_loss | -4.99 | | explained_variance | 0.963 | | learning_rate | 0.000236 | | loss | -0.00849 | | n_updates | 2736 | | policy_gradient_loss | -0.00956 | | value_loss | 0.000239 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 47.9 | | ep_rew_mean | 0.851 | | time/ | | | fps | 1126 | | iterations | 686 | | time_elapsed | 4988 | | total_timesteps | 5619712 | | train/ | | | approx_kl | 0.037196048 | | clip_fraction | 0.249 | | clip_range | 0.143 | | entropy_loss | -5.05 | | explained_variance | 0.967 | | learning_rate | 0.000236 | | loss | -0.0243 | | n_updates | 2740 | | policy_gradient_loss | -0.0162 | | value_loss | 0.000207 | ----------------------------------------- --------------------------------------- | rollout/ | | | ep_len_mean | 48 | | ep_rew_mean | 0.847 | | time/ | | | fps | 1126 | | iterations | 687 | | time_elapsed | 4995 | | total_timesteps | 5627904 | | train/ | | | approx_kl | 0.0347832 | | clip_fraction | 0.201 | | clip_range | 0.143 | | entropy_loss | -5.06 | | explained_variance | 0.98 | | learning_rate | 0.000236 | | loss | -0.0238 | | n_updates | 2744 | | policy_gradient_loss | -0.0165 | | value_loss | 0.000133 | --------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 49.6 | | ep_rew_mean | 0.841 | | time/ | | | fps | 1126 | | iterations | 688 | | time_elapsed | 5003 | | total_timesteps | 5636096 | | train/ | | | approx_kl | 0.04163856 | | clip_fraction | 0.298 | | clip_range | 0.143 | | entropy_loss | -5.11 | | explained_variance | 0.968 | | learning_rate | 0.000236 | | loss | -0.0223 | | n_updates | 2748 | | policy_gradient_loss | -0.019 | | value_loss | 0.000276 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 46 | | ep_rew_mean | 0.853 | | time/ | | | fps | 1126 | | iterations | 689 | | time_elapsed | 5010 | | total_timesteps | 5644288 | | train/ | | | approx_kl | 0.049773544 | | clip_fraction | 0.29 | | clip_range | 0.143 | | entropy_loss | -5.07 | | explained_variance | 0.954 | | learning_rate | 0.000236 | | loss | -0.0248 | | n_updates | 2752 | | policy_gradient_loss | -0.0177 | | value_loss | 0.000401 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 49.6 | | ep_rew_mean | 0.845 | | time/ | | | fps | 1126 | | iterations | 690 | | time_elapsed | 5017 | | total_timesteps | 5652480 | | train/ | | | approx_kl | 0.009857772 | | clip_fraction | 0.198 | | clip_range | 0.143 | | entropy_loss | -4.98 | | explained_variance | 0.993 | | learning_rate | 0.000236 | | loss | 0.0276 | | n_updates | 2756 | | policy_gradient_loss | -0.00352 | | value_loss | 4.78e-05 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 48.7 | | ep_rew_mean | 0.848 | | time/ | | | fps | 1126 | | iterations | 691 | | time_elapsed | 5025 | | total_timesteps | 5660672 | | train/ | | | approx_kl | 0.04864275 | | clip_fraction | 0.292 | | clip_range | 0.143 | | entropy_loss | -5.13 | | explained_variance | 0.933 | | learning_rate | 0.000236 | | loss | -0.0312 | | n_updates | 2760 | | policy_gradient_loss | -0.0178 | | value_loss | 0.000673 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 49.5 | | ep_rew_mean | 0.839 | | time/ | | | fps | 1126 | | iterations | 692 | | time_elapsed | 5032 | | total_timesteps | 5668864 | | train/ | | | approx_kl | 0.07535358 | | clip_fraction | 0.264 | | clip_range | 0.143 | | entropy_loss | -5.12 | | explained_variance | 0.976 | | learning_rate | 0.000236 | | loss | -0.0306 | | n_updates | 2764 | | policy_gradient_loss | -0.0206 | | value_loss | 0.000229 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 49.2 | | ep_rew_mean | 0.844 | | time/ | | | fps | 1126 | | iterations | 693 | | time_elapsed | 5039 | | total_timesteps | 5677056 | | train/ | | | approx_kl | 0.05225493 | | clip_fraction | 0.24 | | clip_range | 0.143 | | entropy_loss | -5.08 | | explained_variance | 0.979 | | learning_rate | 0.000236 | | loss | -0.0153 | | n_updates | 2768 | | policy_gradient_loss | -0.0174 | | value_loss | 0.000176 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 46 | | ep_rew_mean | 0.853 | | time/ | | | fps | 1126 | | iterations | 694 | | time_elapsed | 5047 | | total_timesteps | 5685248 | | train/ | | | approx_kl | 0.053044632 | | clip_fraction | 0.324 | | clip_range | 0.143 | | entropy_loss | -5.18 | | explained_variance | 0.941 | | learning_rate | 0.000236 | | loss | -0.0172 | | n_updates | 2772 | | policy_gradient_loss | -0.0167 | | value_loss | 0.000566 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 47.1 | | ep_rew_mean | 0.851 | | time/ | | | fps | 1126 | | iterations | 695 | | time_elapsed | 5054 | | total_timesteps | 5693440 | | train/ | | | approx_kl | 0.058550157 | | clip_fraction | 0.2 | | clip_range | 0.143 | | entropy_loss | -5.14 | | explained_variance | 0.958 | | learning_rate | 0.000236 | | loss | -0.0242 | | n_updates | 2776 | | policy_gradient_loss | -0.0178 | | value_loss | 0.000308 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 47.7 | | ep_rew_mean | 0.844 | | time/ | | | fps | 1126 | | iterations | 696 | | time_elapsed | 5061 | | total_timesteps | 5701632 | | train/ | | | approx_kl | 0.037914105 | | clip_fraction | 0.286 | | clip_range | 0.143 | | entropy_loss | -5.08 | | explained_variance | 0.96 | | learning_rate | 0.000236 | | loss | -0.0237 | | n_updates | 2780 | | policy_gradient_loss | -0.0151 | | value_loss | 0.00031 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 46 | | ep_rew_mean | 0.853 | | time/ | | | fps | 1126 | | iterations | 697 | | time_elapsed | 5068 | | total_timesteps | 5709824 | | train/ | | | approx_kl | 0.038181815 | | clip_fraction | 0.242 | | clip_range | 0.143 | | entropy_loss | -5.15 | | explained_variance | 0.968 | | learning_rate | 0.000236 | | loss | -0.0127 | | n_updates | 2784 | | policy_gradient_loss | -0.0121 | | value_loss | 0.000229 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 46.1 | | ep_rew_mean | 0.853 | | time/ | | | fps | 1126 | | iterations | 698 | | time_elapsed | 5076 | | total_timesteps | 5718016 | | train/ | | | approx_kl | 0.029108724 | | clip_fraction | 0.234 | | clip_range | 0.143 | | entropy_loss | -5.17 | | explained_variance | 0.946 | | learning_rate | 0.000236 | | loss | -0.0208 | | n_updates | 2788 | | policy_gradient_loss | -0.0128 | | value_loss | 0.000365 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 49.8 | | ep_rew_mean | 0.843 | | time/ | | | fps | 1126 | | iterations | 699 | | time_elapsed | 5083 | | total_timesteps | 5726208 | | train/ | | | approx_kl | 0.03881312 | | clip_fraction | 0.244 | | clip_range | 0.143 | | entropy_loss | -5.18 | | explained_variance | 0.96 | | learning_rate | 0.000236 | | loss | -0.0219 | | n_updates | 2792 | | policy_gradient_loss | -0.0145 | | value_loss | 0.000289 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 53.7 | | ep_rew_mean | 0.831 | | time/ | | | fps | 1126 | | iterations | 700 | | time_elapsed | 5090 | | total_timesteps | 5734400 | | train/ | | | approx_kl | 0.042412892 | | clip_fraction | 0.247 | | clip_range | 0.143 | | entropy_loss | -5.14 | | explained_variance | 0.944 | | learning_rate | 0.000236 | | loss | -0.0214 | | n_updates | 2796 | | policy_gradient_loss | -0.0174 | | value_loss | 0.000451 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 49.7 | | ep_rew_mean | 0.837 | | time/ | | | fps | 1126 | | iterations | 701 | | time_elapsed | 5098 | | total_timesteps | 5742592 | | train/ | | | approx_kl | 0.058085926 | | clip_fraction | 0.275 | | clip_range | 0.143 | | entropy_loss | -5.28 | | explained_variance | 0.966 | | learning_rate | 0.000236 | | loss | -0.0397 | | n_updates | 2800 | | policy_gradient_loss | -0.0237 | | value_loss | 0.000401 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 47.2 | | ep_rew_mean | 0.845 | | time/ | | | fps | 1126 | | iterations | 702 | | time_elapsed | 5105 | | total_timesteps | 5750784 | | train/ | | | approx_kl | 0.051446877 | | clip_fraction | 0.214 | | clip_range | 0.143 | | entropy_loss | -5.13 | | explained_variance | 0.971 | | learning_rate | 0.000236 | | loss | -0.0168 | | n_updates | 2804 | | policy_gradient_loss | -0.0151 | | value_loss | 0.000245 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 50.2 | | ep_rew_mean | 0.831 | | time/ | | | fps | 1126 | | iterations | 703 | | time_elapsed | 5113 | | total_timesteps | 5758976 | | train/ | | | approx_kl | 0.031115629 | | clip_fraction | 0.25 | | clip_range | 0.143 | | entropy_loss | -5.01 | | explained_variance | 0.963 | | learning_rate | 0.000236 | | loss | -0.0171 | | n_updates | 2808 | | policy_gradient_loss | -0.0101 | | value_loss | 0.000241 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 46.4 | | ep_rew_mean | 0.852 | | time/ | | | fps | 1126 | | iterations | 704 | | time_elapsed | 5120 | | total_timesteps | 5767168 | | train/ | | | approx_kl | 0.040584862 | | clip_fraction | 0.262 | | clip_range | 0.143 | | entropy_loss | -5.08 | | explained_variance | 0.964 | | learning_rate | 0.000236 | | loss | -0.0237 | | n_updates | 2812 | | policy_gradient_loss | -0.0174 | | value_loss | 0.000297 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 46 | | ep_rew_mean | 0.853 | | time/ | | | fps | 1126 | | iterations | 705 | | time_elapsed | 5127 | | total_timesteps | 5775360 | | train/ | | | approx_kl | 0.050506927 | | clip_fraction | 0.204 | | clip_range | 0.143 | | entropy_loss | -4.94 | | explained_variance | 0.969 | | learning_rate | 0.000236 | | loss | -0.0125 | | n_updates | 2816 | | policy_gradient_loss | -0.00795 | | value_loss | 0.000153 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 48.8 | | ep_rew_mean | 0.849 | | time/ | | | fps | 1126 | | iterations | 706 | | time_elapsed | 5134 | | total_timesteps | 5783552 | | train/ | | | approx_kl | 0.00870459 | | clip_fraction | 0.185 | | clip_range | 0.143 | | entropy_loss | -4.92 | | explained_variance | 0.995 | | learning_rate | 0.000236 | | loss | -0.00354 | | n_updates | 2820 | | policy_gradient_loss | -0.0031 | | value_loss | 4.43e-05 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 47.6 | | ep_rew_mean | 0.847 | | time/ | | | fps | 1126 | | iterations | 707 | | time_elapsed | 5141 | | total_timesteps | 5791744 | | train/ | | | approx_kl | 0.026312161 | | clip_fraction | 0.228 | | clip_range | 0.143 | | entropy_loss | -5.02 | | explained_variance | 0.963 | | learning_rate | 0.000236 | | loss | -0.0247 | | n_updates | 2824 | | policy_gradient_loss | -0.0135 | | value_loss | 0.000224 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 46 | | ep_rew_mean | 0.853 | | time/ | | | fps | 1126 | | iterations | 708 | | time_elapsed | 5149 | | total_timesteps | 5799936 | | train/ | | | approx_kl | 0.04797593 | | clip_fraction | 0.236 | | clip_range | 0.143 | | entropy_loss | -5.05 | | explained_variance | 0.982 | | learning_rate | 0.000236 | | loss | -0.0242 | | n_updates | 2828 | | policy_gradient_loss | -0.0194 | | value_loss | 0.000167 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 46 | | ep_rew_mean | 0.853 | | time/ | | | fps | 1126 | | iterations | 709 | | time_elapsed | 5156 | | total_timesteps | 5808128 | | train/ | | | approx_kl | 0.013861181 | | clip_fraction | 0.181 | | clip_range | 0.143 | | entropy_loss | -4.94 | | explained_variance | 0.995 | | learning_rate | 0.000236 | | loss | 0.00966 | | n_updates | 2832 | | policy_gradient_loss | -0.00596 | | value_loss | 3.17e-05 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 47.7 | | ep_rew_mean | 0.849 | | time/ | | | fps | 1126 | | iterations | 710 | | time_elapsed | 5163 | | total_timesteps | 5816320 | | train/ | | | approx_kl | 0.011446411 | | clip_fraction | 0.218 | | clip_range | 0.143 | | entropy_loss | -4.85 | | explained_variance | 0.983 | | learning_rate | 0.000236 | | loss | -0.00876 | | n_updates | 2836 | | policy_gradient_loss | -0.00628 | | value_loss | 9.09e-05 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 46.2 | | ep_rew_mean | 0.854 | | time/ | | | fps | 1126 | | iterations | 711 | | time_elapsed | 5170 | | total_timesteps | 5824512 | | train/ | | | approx_kl | 0.027760707 | | clip_fraction | 0.225 | | clip_range | 0.143 | | entropy_loss | -4.96 | | explained_variance | 0.95 | | learning_rate | 0.000236 | | loss | -0.026 | | n_updates | 2840 | | policy_gradient_loss | -0.0112 | | value_loss | 0.000339 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 48.3 | | ep_rew_mean | 0.846 | | time/ | | | fps | 1126 | | iterations | 712 | | time_elapsed | 5178 | | total_timesteps | 5832704 | | train/ | | | approx_kl | 0.020429067 | | clip_fraction | 0.212 | | clip_range | 0.143 | | entropy_loss | -4.97 | | explained_variance | 0.983 | | learning_rate | 0.000236 | | loss | -0.0122 | | n_updates | 2844 | | policy_gradient_loss | -0.00952 | | value_loss | 0.000113 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 48.6 | | ep_rew_mean | 0.845 | | time/ | | | fps | 1126 | | iterations | 713 | | time_elapsed | 5185 | | total_timesteps | 5840896 | | train/ | | | approx_kl | 0.035782814 | | clip_fraction | 0.211 | | clip_range | 0.143 | | entropy_loss | -5.05 | | explained_variance | 0.954 | | learning_rate | 0.000236 | | loss | -0.0159 | | n_updates | 2848 | | policy_gradient_loss | -0.0101 | | value_loss | 0.000299 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 47.9 | | ep_rew_mean | 0.85 | | time/ | | | fps | 1126 | | iterations | 714 | | time_elapsed | 5192 | | total_timesteps | 5849088 | | train/ | | | approx_kl | 0.03729223 | | clip_fraction | 0.239 | | clip_range | 0.143 | | entropy_loss | -5 | | explained_variance | 0.957 | | learning_rate | 0.000236 | | loss | -0.0241 | | n_updates | 2852 | | policy_gradient_loss | -0.0143 | | value_loss | 0.000314 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 46 | | ep_rew_mean | 0.853 | | time/ | | | fps | 1126 | | iterations | 715 | | time_elapsed | 5199 | | total_timesteps | 5857280 | | train/ | | | approx_kl | 0.031190388 | | clip_fraction | 0.27 | | clip_range | 0.143 | | entropy_loss | -5.02 | | explained_variance | 0.976 | | learning_rate | 0.000236 | | loss | -0.0201 | | n_updates | 2856 | | policy_gradient_loss | -0.0155 | | value_loss | 0.000189 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 46 | | ep_rew_mean | 0.853 | | time/ | | | fps | 1126 | | iterations | 716 | | time_elapsed | 5207 | | total_timesteps | 5865472 | | train/ | | | approx_kl | 0.029389545 | | clip_fraction | 0.16 | | clip_range | 0.143 | | entropy_loss | -5.02 | | explained_variance | 0.992 | | learning_rate | 0.000236 | | loss | -0.0157 | | n_updates | 2860 | | policy_gradient_loss | -0.0132 | | value_loss | 5.72e-05 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 47.5 | | ep_rew_mean | 0.845 | | time/ | | | fps | 1126 | | iterations | 717 | | time_elapsed | 5214 | | total_timesteps | 5873664 | | train/ | | | approx_kl | 0.022747431 | | clip_fraction | 0.189 | | clip_range | 0.143 | | entropy_loss | -4.99 | | explained_variance | 0.992 | | learning_rate | 0.000235 | | loss | -0.0134 | | n_updates | 2864 | | policy_gradient_loss | -0.00887 | | value_loss | 7.38e-05 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 48.1 | | ep_rew_mean | 0.839 | | time/ | | | fps | 1126 | | iterations | 718 | | time_elapsed | 5221 | | total_timesteps | 5881856 | | train/ | | | approx_kl | 0.039368197 | | clip_fraction | 0.238 | | clip_range | 0.143 | | entropy_loss | -5.12 | | explained_variance | 0.971 | | learning_rate | 0.000235 | | loss | -0.0225 | | n_updates | 2868 | | policy_gradient_loss | -0.0167 | | value_loss | 0.000243 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 46 | | ep_rew_mean | 0.853 | | time/ | | | fps | 1126 | | iterations | 719 | | time_elapsed | 5229 | | total_timesteps | 5890048 | | train/ | | | approx_kl | 0.03455733 | | clip_fraction | 0.248 | | clip_range | 0.143 | | entropy_loss | -5.12 | | explained_variance | 0.961 | | learning_rate | 0.000235 | | loss | -0.0267 | | n_updates | 2872 | | policy_gradient_loss | -0.0173 | | value_loss | 0.000348 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 49.8 | | ep_rew_mean | 0.846 | | time/ | | | fps | 1126 | | iterations | 720 | | time_elapsed | 5236 | | total_timesteps | 5898240 | | train/ | | | approx_kl | 0.029886011 | | clip_fraction | 0.203 | | clip_range | 0.143 | | entropy_loss | -5.02 | | explained_variance | 0.964 | | learning_rate | 0.000235 | | loss | -0.0156 | | n_updates | 2876 | | policy_gradient_loss | -0.00798 | | value_loss | 0.000236 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 47 | | ep_rew_mean | 0.852 | | time/ | | | fps | 1126 | | iterations | 721 | | time_elapsed | 5243 | | total_timesteps | 5906432 | | train/ | | | approx_kl | 0.045287192 | | clip_fraction | 0.196 | | clip_range | 0.143 | | entropy_loss | -5.09 | | explained_variance | 0.983 | | learning_rate | 0.000235 | | loss | -0.0162 | | n_updates | 2880 | | policy_gradient_loss | -0.0147 | | value_loss | 0.000125 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 52.3 | | ep_rew_mean | 0.831 | | time/ | | | fps | 1126 | | iterations | 722 | | time_elapsed | 5251 | | total_timesteps | 5914624 | | train/ | | | approx_kl | 0.04054501 | | clip_fraction | 0.199 | | clip_range | 0.143 | | entropy_loss | -5.09 | | explained_variance | 0.935 | | learning_rate | 0.000235 | | loss | -0.017 | | n_updates | 2884 | | policy_gradient_loss | -0.0121 | | value_loss | 0.00039 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 53.3 | | ep_rew_mean | 0.835 | | time/ | | | fps | 1126 | | iterations | 723 | | time_elapsed | 5258 | | total_timesteps | 5922816 | | train/ | | | approx_kl | 0.050431214 | | clip_fraction | 0.28 | | clip_range | 0.143 | | entropy_loss | -5.22 | | explained_variance | 0.946 | | learning_rate | 0.000235 | | loss | -0.0331 | | n_updates | 2888 | | policy_gradient_loss | -0.0191 | | value_loss | 0.000533 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 49.1 | | ep_rew_mean | 0.844 | | time/ | | | fps | 1126 | | iterations | 724 | | time_elapsed | 5265 | | total_timesteps | 5931008 | | train/ | | | approx_kl | 0.045170095 | | clip_fraction | 0.243 | | clip_range | 0.143 | | entropy_loss | -5.28 | | explained_variance | 0.972 | | learning_rate | 0.000235 | | loss | -0.0315 | | n_updates | 2892 | | policy_gradient_loss | -0.0225 | | value_loss | 0.000293 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 50.6 | | ep_rew_mean | 0.84 | | time/ | | | fps | 1126 | | iterations | 725 | | time_elapsed | 5273 | | total_timesteps | 5939200 | | train/ | | | approx_kl | 0.035973076 | | clip_fraction | 0.276 | | clip_range | 0.143 | | entropy_loss | -5.12 | | explained_variance | 0.956 | | learning_rate | 0.000235 | | loss | -0.0242 | | n_updates | 2896 | | policy_gradient_loss | -0.0165 | | value_loss | 0.00033 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 47 | | ep_rew_mean | 0.852 | | time/ | | | fps | 1126 | | iterations | 726 | | time_elapsed | 5280 | | total_timesteps | 5947392 | | train/ | | | approx_kl | 0.05976686 | | clip_fraction | 0.285 | | clip_range | 0.143 | | entropy_loss | -5.24 | | explained_variance | 0.951 | | learning_rate | 0.000235 | | loss | -0.0363 | | n_updates | 2900 | | policy_gradient_loss | -0.0241 | | value_loss | 0.000538 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 49.7 | | ep_rew_mean | 0.842 | | time/ | | | fps | 1126 | | iterations | 727 | | time_elapsed | 5287 | | total_timesteps | 5955584 | | train/ | | | approx_kl | 0.034210984 | | clip_fraction | 0.24 | | clip_range | 0.143 | | entropy_loss | -5.01 | | explained_variance | 0.955 | | learning_rate | 0.000235 | | loss | -0.0198 | | n_updates | 2904 | | policy_gradient_loss | -0.0102 | | value_loss | 0.000284 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 47.7 | | ep_rew_mean | 0.842 | | time/ | | | fps | 1126 | | iterations | 728 | | time_elapsed | 5295 | | total_timesteps | 5963776 | | train/ | | | approx_kl | 0.036749084 | | clip_fraction | 0.244 | | clip_range | 0.143 | | entropy_loss | -5.12 | | explained_variance | 0.959 | | learning_rate | 0.000235 | | loss | -0.0236 | | n_updates | 2908 | | policy_gradient_loss | -0.0152 | | value_loss | 0.000316 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 47.6 | | ep_rew_mean | 0.848 | | time/ | | | fps | 1126 | | iterations | 729 | | time_elapsed | 5302 | | total_timesteps | 5971968 | | train/ | | | approx_kl | 0.038757585 | | clip_fraction | 0.257 | | clip_range | 0.143 | | entropy_loss | -5.08 | | explained_variance | 0.944 | | learning_rate | 0.000235 | | loss | -0.0194 | | n_updates | 2912 | | policy_gradient_loss | -0.0154 | | value_loss | 0.000443 | ----------------------------------------- --------------------------------------- | rollout/ | | | ep_len_mean | 47.7 | | ep_rew_mean | 0.847 | | time/ | | | fps | 1126 | | iterations | 730 | | time_elapsed | 5309 | | total_timesteps | 5980160 | | train/ | | | approx_kl | 0.0453797 | | clip_fraction | 0.259 | | clip_range | 0.143 | | entropy_loss | -5.26 | | explained_variance | 0.966 | | learning_rate | 0.000235 | | loss | -0.0325 | | n_updates | 2916 | | policy_gradient_loss | -0.0224 | | value_loss | 0.000317 | --------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 51.6 | | ep_rew_mean | 0.842 | | time/ | | | fps | 1126 | | iterations | 731 | | time_elapsed | 5317 | | total_timesteps | 5988352 | | train/ | | | approx_kl | 0.03852643 | | clip_fraction | 0.226 | | clip_range | 0.143 | | entropy_loss | -5.15 | | explained_variance | 0.986 | | learning_rate | 0.000235 | | loss | -0.0299 | | n_updates | 2920 | | policy_gradient_loss | -0.0187 | | value_loss | 0.000117 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 56.9 | | ep_rew_mean | 0.83 | | time/ | | | fps | 1126 | | iterations | 732 | | time_elapsed | 5324 | | total_timesteps | 5996544 | | train/ | | | approx_kl | 0.04784715 | | clip_fraction | 0.307 | | clip_range | 0.143 | | entropy_loss | -5.18 | | explained_variance | 0.948 | | learning_rate | 0.000235 | | loss | -0.0314 | | n_updates | 2924 | | policy_gradient_loss | -0.0193 | | value_loss | 0.000505 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 50.4 | | ep_rew_mean | 0.843 | | time/ | | | fps | 1126 | | iterations | 733 | | time_elapsed | 5331 | | total_timesteps | 6004736 | | train/ | | | approx_kl | 0.06175911 | | clip_fraction | 0.276 | | clip_range | 0.143 | | entropy_loss | -5.42 | | explained_variance | 0.966 | | learning_rate | 0.000235 | | loss | -0.0377 | | n_updates | 2928 | | policy_gradient_loss | -0.0283 | | value_loss | 0.000451 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 48.5 | | ep_rew_mean | 0.839 | | time/ | | | fps | 1126 | | iterations | 734 | | time_elapsed | 5339 | | total_timesteps | 6012928 | | train/ | | | approx_kl | 0.048298042 | | clip_fraction | 0.255 | | clip_range | 0.142 | | entropy_loss | -5.21 | | explained_variance | 0.964 | | learning_rate | 0.000235 | | loss | -0.0298 | | n_updates | 2932 | | policy_gradient_loss | -0.0179 | | value_loss | 0.000372 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 47.6 | | ep_rew_mean | 0.851 | | time/ | | | fps | 1126 | | iterations | 735 | | time_elapsed | 5346 | | total_timesteps | 6021120 | | train/ | | | approx_kl | 0.042535838 | | clip_fraction | 0.271 | | clip_range | 0.142 | | entropy_loss | -5.21 | | explained_variance | 0.973 | | learning_rate | 0.000235 | | loss | -0.0199 | | n_updates | 2936 | | policy_gradient_loss | -0.0164 | | value_loss | 0.000257 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 47.1 | | ep_rew_mean | 0.844 | | time/ | | | fps | 1126 | | iterations | 736 | | time_elapsed | 5353 | | total_timesteps | 6029312 | | train/ | | | approx_kl | 0.034904987 | | clip_fraction | 0.282 | | clip_range | 0.142 | | entropy_loss | -5.25 | | explained_variance | 0.959 | | learning_rate | 0.000235 | | loss | -0.0259 | | n_updates | 2940 | | policy_gradient_loss | -0.0185 | | value_loss | 0.000341 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 51.3 | | ep_rew_mean | 0.827 | | time/ | | | fps | 1126 | | iterations | 737 | | time_elapsed | 5360 | | total_timesteps | 6037504 | | train/ | | | approx_kl | 0.019801997 | | clip_fraction | 0.242 | | clip_range | 0.142 | | entropy_loss | -5.14 | | explained_variance | 0.97 | | learning_rate | 0.000235 | | loss | -0.0133 | | n_updates | 2944 | | policy_gradient_loss | -0.0103 | | value_loss | 0.000201 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 51.5 | | ep_rew_mean | 0.833 | | time/ | | | fps | 1126 | | iterations | 738 | | time_elapsed | 5368 | | total_timesteps | 6045696 | | train/ | | | approx_kl | 0.04305493 | | clip_fraction | 0.275 | | clip_range | 0.142 | | entropy_loss | -5.27 | | explained_variance | 0.962 | | learning_rate | 0.000235 | | loss | -0.0274 | | n_updates | 2948 | | policy_gradient_loss | -0.0205 | | value_loss | 0.000372 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 51.6 | | ep_rew_mean | 0.84 | | time/ | | | fps | 1126 | | iterations | 739 | | time_elapsed | 5375 | | total_timesteps | 6053888 | | train/ | | | approx_kl | 0.03373812 | | clip_fraction | 0.281 | | clip_range | 0.142 | | entropy_loss | -5.3 | | explained_variance | 0.969 | | learning_rate | 0.000235 | | loss | -0.0236 | | n_updates | 2952 | | policy_gradient_loss | -0.0196 | | value_loss | 0.000323 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 50 | | ep_rew_mean | 0.841 | | time/ | | | fps | 1126 | | iterations | 740 | | time_elapsed | 5382 | | total_timesteps | 6062080 | | train/ | | | approx_kl | 0.048344314 | | clip_fraction | 0.305 | | clip_range | 0.142 | | entropy_loss | -5.3 | | explained_variance | 0.963 | | learning_rate | 0.000235 | | loss | -0.0211 | | n_updates | 2956 | | policy_gradient_loss | -0.0213 | | value_loss | 0.000393 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 46.3 | | ep_rew_mean | 0.854 | | time/ | | | fps | 1126 | | iterations | 741 | | time_elapsed | 5390 | | total_timesteps | 6070272 | | train/ | | | approx_kl | 0.041593716 | | clip_fraction | 0.258 | | clip_range | 0.142 | | entropy_loss | -5.28 | | explained_variance | 0.971 | | learning_rate | 0.000235 | | loss | -0.0332 | | n_updates | 2960 | | policy_gradient_loss | -0.0192 | | value_loss | 0.00029 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 50.2 | | ep_rew_mean | 0.842 | | time/ | | | fps | 1126 | | iterations | 742 | | time_elapsed | 5396 | | total_timesteps | 6078464 | | train/ | | | approx_kl | 0.016287819 | | clip_fraction | 0.24 | | clip_range | 0.142 | | entropy_loss | -5.1 | | explained_variance | 0.975 | | learning_rate | 0.000235 | | loss | -0.0143 | | n_updates | 2964 | | policy_gradient_loss | -0.00889 | | value_loss | 0.000156 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 48.3 | | ep_rew_mean | 0.846 | | time/ | | | fps | 1126 | | iterations | 743 | | time_elapsed | 5404 | | total_timesteps | 6086656 | | train/ | | | approx_kl | 0.05024436 | | clip_fraction | 0.271 | | clip_range | 0.142 | | entropy_loss | -5.23 | | explained_variance | 0.942 | | learning_rate | 0.000235 | | loss | -0.0206 | | n_updates | 2968 | | policy_gradient_loss | -0.0171 | | value_loss | 0.000506 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 51 | | ep_rew_mean | 0.841 | | time/ | | | fps | 1126 | | iterations | 744 | | time_elapsed | 5411 | | total_timesteps | 6094848 | | train/ | | | approx_kl | 0.03224071 | | clip_fraction | 0.241 | | clip_range | 0.142 | | entropy_loss | -5.21 | | explained_variance | 0.957 | | learning_rate | 0.000235 | | loss | -0.0188 | | n_updates | 2972 | | policy_gradient_loss | -0.0153 | | value_loss | 0.000331 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 49.8 | | ep_rew_mean | 0.841 | | time/ | | | fps | 1126 | | iterations | 745 | | time_elapsed | 5418 | | total_timesteps | 6103040 | | train/ | | | approx_kl | 0.044510987 | | clip_fraction | 0.269 | | clip_range | 0.142 | | entropy_loss | -5.32 | | explained_variance | 0.962 | | learning_rate | 0.000235 | | loss | -0.0286 | | n_updates | 2976 | | policy_gradient_loss | -0.0204 | | value_loss | 0.000371 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 51.6 | | ep_rew_mean | 0.843 | | time/ | | | fps | 1126 | | iterations | 746 | | time_elapsed | 5426 | | total_timesteps | 6111232 | | train/ | | | approx_kl | 0.04014173 | | clip_fraction | 0.289 | | clip_range | 0.142 | | entropy_loss | -5.28 | | explained_variance | 0.973 | | learning_rate | 0.000235 | | loss | -0.0307 | | n_updates | 2980 | | policy_gradient_loss | -0.0187 | | value_loss | 0.000296 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 51.1 | | ep_rew_mean | 0.839 | | time/ | | | fps | 1126 | | iterations | 747 | | time_elapsed | 5433 | | total_timesteps | 6119424 | | train/ | | | approx_kl | 0.038560018 | | clip_fraction | 0.244 | | clip_range | 0.142 | | entropy_loss | -5.28 | | explained_variance | 0.981 | | learning_rate | 0.000235 | | loss | -0.0257 | | n_updates | 2984 | | policy_gradient_loss | -0.0185 | | value_loss | 0.000181 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 47.6 | | ep_rew_mean | 0.848 | | time/ | | | fps | 1126 | | iterations | 748 | | time_elapsed | 5440 | | total_timesteps | 6127616 | | train/ | | | approx_kl | 0.048225008 | | clip_fraction | 0.324 | | clip_range | 0.142 | | entropy_loss | -5.36 | | explained_variance | 0.958 | | learning_rate | 0.000235 | | loss | -0.0312 | | n_updates | 2988 | | policy_gradient_loss | -0.0199 | | value_loss | 0.000507 | ----------------------------------------- --------------------------------------- | rollout/ | | | ep_len_mean | 47 | | ep_rew_mean | 0.851 | | time/ | | | fps | 1126 | | iterations | 749 | | time_elapsed | 5447 | | total_timesteps | 6135808 | | train/ | | | approx_kl | 0.0355388 | | clip_fraction | 0.239 | | clip_range | 0.142 | | entropy_loss | -5.17 | | explained_variance | 0.962 | | learning_rate | 0.000235 | | loss | -0.026 | | n_updates | 2992 | | policy_gradient_loss | -0.0148 | | value_loss | 0.000295 | --------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 46 | | ep_rew_mean | 0.853 | | time/ | | | fps | 1126 | | iterations | 750 | | time_elapsed | 5455 | | total_timesteps | 6144000 | | train/ | | | approx_kl | 0.035041135 | | clip_fraction | 0.22 | | clip_range | 0.142 | | entropy_loss | -5.1 | | explained_variance | 0.964 | | learning_rate | 0.000235 | | loss | -0.0191 | | n_updates | 2996 | | policy_gradient_loss | -0.0106 | | value_loss | 0.000233 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 52.1 | | ep_rew_mean | 0.836 | | time/ | | | fps | 1126 | | iterations | 751 | | time_elapsed | 5462 | | total_timesteps | 6152192 | | train/ | | | approx_kl | 0.028162979 | | clip_fraction | 0.2 | | clip_range | 0.142 | | entropy_loss | -5.1 | | explained_variance | 0.982 | | learning_rate | 0.000235 | | loss | -0.0186 | | n_updates | 3000 | | policy_gradient_loss | -0.0119 | | value_loss | 0.000123 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 48.1 | | ep_rew_mean | 0.843 | | time/ | | | fps | 1126 | | iterations | 752 | | time_elapsed | 5469 | | total_timesteps | 6160384 | | train/ | | | approx_kl | 0.038256727 | | clip_fraction | 0.251 | | clip_range | 0.142 | | entropy_loss | -5.21 | | explained_variance | 0.966 | | learning_rate | 0.000235 | | loss | -0.0139 | | n_updates | 3004 | | policy_gradient_loss | -0.0162 | | value_loss | 0.000307 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 46 | | ep_rew_mean | 0.853 | | time/ | | | fps | 1126 | | iterations | 753 | | time_elapsed | 5477 | | total_timesteps | 6168576 | | train/ | | | approx_kl | 0.05544287 | | clip_fraction | 0.275 | | clip_range | 0.142 | | entropy_loss | -5.18 | | explained_variance | 0.973 | | learning_rate | 0.000235 | | loss | -0.0125 | | n_updates | 3008 | | policy_gradient_loss | -0.015 | | value_loss | 0.000218 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 50.2 | | ep_rew_mean | 0.834 | | time/ | | | fps | 1126 | | iterations | 754 | | time_elapsed | 5484 | | total_timesteps | 6176768 | | train/ | | | approx_kl | 0.058045685 | | clip_fraction | 0.239 | | clip_range | 0.142 | | entropy_loss | -5.16 | | explained_variance | 0.98 | | learning_rate | 0.000235 | | loss | -0.0199 | | n_updates | 3012 | | policy_gradient_loss | -0.0162 | | value_loss | 0.000151 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 47.4 | | ep_rew_mean | 0.847 | | time/ | | | fps | 1126 | | iterations | 755 | | time_elapsed | 5491 | | total_timesteps | 6184960 | | train/ | | | approx_kl | 0.057210833 | | clip_fraction | 0.251 | | clip_range | 0.142 | | entropy_loss | -5.25 | | explained_variance | 0.971 | | learning_rate | 0.000235 | | loss | -0.0344 | | n_updates | 3016 | | policy_gradient_loss | -0.0205 | | value_loss | 0.000297 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 46.3 | | ep_rew_mean | 0.853 | | time/ | | | fps | 1126 | | iterations | 756 | | time_elapsed | 5498 | | total_timesteps | 6193152 | | train/ | | | approx_kl | 0.03760905 | | clip_fraction | 0.281 | | clip_range | 0.142 | | entropy_loss | -5.16 | | explained_variance | 0.957 | | learning_rate | 0.000235 | | loss | -0.0248 | | n_updates | 3020 | | policy_gradient_loss | -0.0174 | | value_loss | 0.000372 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 47.7 | | ep_rew_mean | 0.846 | | time/ | | | fps | 1126 | | iterations | 757 | | time_elapsed | 5505 | | total_timesteps | 6201344 | | train/ | | | approx_kl | 0.038085088 | | clip_fraction | 0.23 | | clip_range | 0.142 | | entropy_loss | -5.1 | | explained_variance | 0.961 | | learning_rate | 0.000235 | | loss | -0.0171 | | n_updates | 3024 | | policy_gradient_loss | -0.0107 | | value_loss | 0.000274 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 46 | | ep_rew_mean | 0.853 | | time/ | | | fps | 1126 | | iterations | 758 | | time_elapsed | 5513 | | total_timesteps | 6209536 | | train/ | | | approx_kl | 0.047488715 | | clip_fraction | 0.274 | | clip_range | 0.142 | | entropy_loss | -5.19 | | explained_variance | 0.972 | | learning_rate | 0.000235 | | loss | -0.0243 | | n_updates | 3028 | | policy_gradient_loss | -0.0157 | | value_loss | 0.000241 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 46 | | ep_rew_mean | 0.853 | | time/ | | | fps | 1126 | | iterations | 759 | | time_elapsed | 5520 | | total_timesteps | 6217728 | | train/ | | | approx_kl | 0.039855327 | | clip_fraction | 0.21 | | clip_range | 0.142 | | entropy_loss | -5.15 | | explained_variance | 0.988 | | learning_rate | 0.000235 | | loss | -0.0263 | | n_updates | 3032 | | policy_gradient_loss | -0.0144 | | value_loss | 9.13e-05 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 46 | | ep_rew_mean | 0.853 | | time/ | | | fps | 1126 | | iterations | 760 | | time_elapsed | 5527 | | total_timesteps | 6225920 | | train/ | | | approx_kl | 0.023532707 | | clip_fraction | 0.201 | | clip_range | 0.142 | | entropy_loss | -5.07 | | explained_variance | 0.964 | | learning_rate | 0.000235 | | loss | -0.0079 | | n_updates | 3036 | | policy_gradient_loss | -0.00859 | | value_loss | 0.000194 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 48.1 | | ep_rew_mean | 0.846 | | time/ | | | fps | 1126 | | iterations | 761 | | time_elapsed | 5534 | | total_timesteps | 6234112 | | train/ | | | approx_kl | 0.025123313 | | clip_fraction | 0.214 | | clip_range | 0.142 | | entropy_loss | -5.1 | | explained_variance | 0.98 | | learning_rate | 0.000235 | | loss | -0.0135 | | n_updates | 3040 | | policy_gradient_loss | -0.0114 | | value_loss | 0.00011 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 46.2 | | ep_rew_mean | 0.854 | | time/ | | | fps | 1126 | | iterations | 762 | | time_elapsed | 5542 | | total_timesteps | 6242304 | | train/ | | | approx_kl | 0.037490234 | | clip_fraction | 0.271 | | clip_range | 0.142 | | entropy_loss | -5.18 | | explained_variance | 0.971 | | learning_rate | 0.000235 | | loss | -0.0226 | | n_updates | 3044 | | policy_gradient_loss | -0.0151 | | value_loss | 0.000232 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 49 | | ep_rew_mean | 0.848 | | time/ | | | fps | 1126 | | iterations | 763 | | time_elapsed | 5549 | | total_timesteps | 6250496 | | train/ | | | approx_kl | 0.03347466 | | clip_fraction | 0.227 | | clip_range | 0.142 | | entropy_loss | -5.22 | | explained_variance | 0.975 | | learning_rate | 0.000235 | | loss | -0.0192 | | n_updates | 3048 | | policy_gradient_loss | -0.0178 | | value_loss | 0.000203 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 52.7 | | ep_rew_mean | 0.84 | | time/ | | | fps | 1126 | | iterations | 764 | | time_elapsed | 5557 | | total_timesteps | 6258688 | | train/ | | | approx_kl | 0.033448763 | | clip_fraction | 0.22 | | clip_range | 0.142 | | entropy_loss | -5.23 | | explained_variance | 0.971 | | learning_rate | 0.000235 | | loss | -0.0171 | | n_updates | 3052 | | policy_gradient_loss | -0.0151 | | value_loss | 0.000227 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 53.8 | | ep_rew_mean | 0.835 | | time/ | | | fps | 1126 | | iterations | 765 | | time_elapsed | 5564 | | total_timesteps | 6266880 | | train/ | | | approx_kl | 0.040871978 | | clip_fraction | 0.294 | | clip_range | 0.142 | | entropy_loss | -5.33 | | explained_variance | 0.96 | | learning_rate | 0.000235 | | loss | -0.0267 | | n_updates | 3056 | | policy_gradient_loss | -0.0209 | | value_loss | 0.000444 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 48.7 | | ep_rew_mean | 0.849 | | time/ | | | fps | 1126 | | iterations | 766 | | time_elapsed | 5571 | | total_timesteps | 6275072 | | train/ | | | approx_kl | 0.03903518 | | clip_fraction | 0.261 | | clip_range | 0.142 | | entropy_loss | -5.21 | | explained_variance | 0.967 | | learning_rate | 0.000234 | | loss | -0.0304 | | n_updates | 3060 | | policy_gradient_loss | -0.0171 | | value_loss | 0.0003 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 49.6 | | ep_rew_mean | 0.845 | | time/ | | | fps | 1126 | | iterations | 767 | | time_elapsed | 5579 | | total_timesteps | 6283264 | | train/ | | | approx_kl | 0.030962426 | | clip_fraction | 0.234 | | clip_range | 0.142 | | entropy_loss | -5.13 | | explained_variance | 0.973 | | learning_rate | 0.000234 | | loss | -0.0216 | | n_updates | 3064 | | policy_gradient_loss | -0.0147 | | value_loss | 0.000202 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 46 | | ep_rew_mean | 0.853 | | time/ | | | fps | 1126 | | iterations | 768 | | time_elapsed | 5586 | | total_timesteps | 6291456 | | train/ | | | approx_kl | 0.035079446 | | clip_fraction | 0.257 | | clip_range | 0.142 | | entropy_loss | -5.16 | | explained_variance | 0.977 | | learning_rate | 0.000234 | | loss | -0.0197 | | n_updates | 3068 | | policy_gradient_loss | -0.0143 | | value_loss | 0.00021 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 46 | | ep_rew_mean | 0.853 | | time/ | | | fps | 1126 | | iterations | 769 | | time_elapsed | 5593 | | total_timesteps | 6299648 | | train/ | | | approx_kl | 0.032604642 | | clip_fraction | 0.187 | | clip_range | 0.142 | | entropy_loss | -5.04 | | explained_variance | 0.984 | | learning_rate | 0.000234 | | loss | -0.00746 | | n_updates | 3072 | | policy_gradient_loss | -0.00535 | | value_loss | 8.02e-05 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 46 | | ep_rew_mean | 0.853 | | time/ | | | fps | 1126 | | iterations | 770 | | time_elapsed | 5601 | | total_timesteps | 6307840 | | train/ | | | approx_kl | 0.018493613 | | clip_fraction | 0.245 | | clip_range | 0.142 | | entropy_loss | -5.08 | | explained_variance | 0.977 | | learning_rate | 0.000234 | | loss | -0.0141 | | n_updates | 3076 | | policy_gradient_loss | -0.00727 | | value_loss | 0.00013 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 48.3 | | ep_rew_mean | 0.852 | | time/ | | | fps | 1126 | | iterations | 771 | | time_elapsed | 5608 | | total_timesteps | 6316032 | | train/ | | | approx_kl | 0.028190378 | | clip_fraction | 0.256 | | clip_range | 0.142 | | entropy_loss | -5.05 | | explained_variance | 0.974 | | learning_rate | 0.000234 | | loss | -0.0181 | | n_updates | 3080 | | policy_gradient_loss | -0.0113 | | value_loss | 0.000127 | ----------------------------------------- --------------------------------------- | rollout/ | | | ep_len_mean | 46.5 | | ep_rew_mean | 0.852 | | time/ | | | fps | 1126 | | iterations | 772 | | time_elapsed | 5616 | | total_timesteps | 6324224 | | train/ | | | approx_kl | 0.0286576 | | clip_fraction | 0.237 | | clip_range | 0.142 | | entropy_loss | -5.03 | | explained_variance | 0.97 | | learning_rate | 0.000234 | | loss | -0.0195 | | n_updates | 3084 | | policy_gradient_loss | -0.0135 | | value_loss | 0.000219 | --------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 47.5 | | ep_rew_mean | 0.846 | | time/ | | | fps | 1126 | | iterations | 773 | | time_elapsed | 5623 | | total_timesteps | 6332416 | | train/ | | | approx_kl | 0.026856178 | | clip_fraction | 0.204 | | clip_range | 0.142 | | entropy_loss | -5.01 | | explained_variance | 0.977 | | learning_rate | 0.000234 | | loss | -0.0118 | | n_updates | 3088 | | policy_gradient_loss | -0.00806 | | value_loss | 0.000132 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 48 | | ep_rew_mean | 0.843 | | time/ | | | fps | 1126 | | iterations | 774 | | time_elapsed | 5630 | | total_timesteps | 6340608 | | train/ | | | approx_kl | 0.022221375 | | clip_fraction | 0.215 | | clip_range | 0.142 | | entropy_loss | -5 | | explained_variance | 0.984 | | learning_rate | 0.000234 | | loss | -0.0146 | | n_updates | 3092 | | policy_gradient_loss | -0.0096 | | value_loss | 0.000122 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 46 | | ep_rew_mean | 0.853 | | time/ | | | fps | 1126 | | iterations | 775 | | time_elapsed | 5637 | | total_timesteps | 6348800 | | train/ | | | approx_kl | 0.037792154 | | clip_fraction | 0.247 | | clip_range | 0.142 | | entropy_loss | -5.01 | | explained_variance | 0.978 | | learning_rate | 0.000234 | | loss | -0.0159 | | n_updates | 3096 | | policy_gradient_loss | -0.013 | | value_loss | 0.00017 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 46 | | ep_rew_mean | 0.853 | | time/ | | | fps | 1126 | | iterations | 776 | | time_elapsed | 5645 | | total_timesteps | 6356992 | | train/ | | | approx_kl | 0.020882806 | | clip_fraction | 0.239 | | clip_range | 0.142 | | entropy_loss | -5 | | explained_variance | 0.986 | | learning_rate | 0.000234 | | loss | -0.0167 | | n_updates | 3100 | | policy_gradient_loss | -0.0096 | | value_loss | 0.000112 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 47.7 | | ep_rew_mean | 0.85 | | time/ | | | fps | 1126 | | iterations | 777 | | time_elapsed | 5652 | | total_timesteps | 6365184 | | train/ | | | approx_kl | 0.022384431 | | clip_fraction | 0.174 | | clip_range | 0.142 | | entropy_loss | -4.99 | | explained_variance | 0.991 | | learning_rate | 0.000234 | | loss | -0.00844 | | n_updates | 3104 | | policy_gradient_loss | -0.00749 | | value_loss | 7.09e-05 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 46.2 | | ep_rew_mean | 0.854 | | time/ | | | fps | 1126 | | iterations | 778 | | time_elapsed | 5659 | | total_timesteps | 6373376 | | train/ | | | approx_kl | 0.039117202 | | clip_fraction | 0.216 | | clip_range | 0.142 | | entropy_loss | -5.04 | | explained_variance | 0.975 | | learning_rate | 0.000234 | | loss | -0.0238 | | n_updates | 3108 | | policy_gradient_loss | -0.016 | | value_loss | 0.000178 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 46 | | ep_rew_mean | 0.853 | | time/ | | | fps | 1126 | | iterations | 779 | | time_elapsed | 5667 | | total_timesteps | 6381568 | | train/ | | | approx_kl | 0.031001236 | | clip_fraction | 0.244 | | clip_range | 0.142 | | entropy_loss | -5 | | explained_variance | 0.979 | | learning_rate | 0.000234 | | loss | -0.016 | | n_updates | 3112 | | policy_gradient_loss | -0.0142 | | value_loss | 0.000152 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 46.2 | | ep_rew_mean | 0.854 | | time/ | | | fps | 1126 | | iterations | 780 | | time_elapsed | 5674 | | total_timesteps | 6389760 | | train/ | | | approx_kl | 0.042975467 | | clip_fraction | 0.229 | | clip_range | 0.142 | | entropy_loss | -5.05 | | explained_variance | 0.984 | | learning_rate | 0.000234 | | loss | -0.0147 | | n_updates | 3116 | | policy_gradient_loss | -0.0157 | | value_loss | 0.000129 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 46.2 | | ep_rew_mean | 0.854 | | time/ | | | fps | 1126 | | iterations | 781 | | time_elapsed | 5681 | | total_timesteps | 6397952 | | train/ | | | approx_kl | 0.012288848 | | clip_fraction | 0.22 | | clip_range | 0.142 | | entropy_loss | -4.94 | | explained_variance | 0.983 | | learning_rate | 0.000234 | | loss | -0.014 | | n_updates | 3120 | | policy_gradient_loss | -0.00573 | | value_loss | 7.39e-05 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 46.9 | | ep_rew_mean | 0.847 | | time/ | | | fps | 1125 | | iterations | 782 | | time_elapsed | 5689 | | total_timesteps | 6406144 | | train/ | | | approx_kl | 0.012277699 | | clip_fraction | 0.212 | | clip_range | 0.142 | | entropy_loss | -4.95 | | explained_variance | 0.987 | | learning_rate | 0.000234 | | loss | -0.0131 | | n_updates | 3124 | | policy_gradient_loss | -0.00448 | | value_loss | 8.29e-05 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 50.1 | | ep_rew_mean | 0.836 | | time/ | | | fps | 1125 | | iterations | 783 | | time_elapsed | 5696 | | total_timesteps | 6414336 | | train/ | | | approx_kl | 0.020281263 | | clip_fraction | 0.21 | | clip_range | 0.142 | | entropy_loss | -4.96 | | explained_variance | 0.983 | | learning_rate | 0.000234 | | loss | -0.00463 | | n_updates | 3128 | | policy_gradient_loss | -0.00717 | | value_loss | 0.000108 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 46 | | ep_rew_mean | 0.853 | | time/ | | | fps | 1125 | | iterations | 784 | | time_elapsed | 5704 | | total_timesteps | 6422528 | | train/ | | | approx_kl | 0.043180197 | | clip_fraction | 0.245 | | clip_range | 0.142 | | entropy_loss | -5.15 | | explained_variance | 0.973 | | learning_rate | 0.000234 | | loss | -0.0245 | | n_updates | 3132 | | policy_gradient_loss | -0.0181 | | value_loss | 0.000256 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 48.4 | | ep_rew_mean | 0.847 | | time/ | | | fps | 1125 | | iterations | 785 | | time_elapsed | 5711 | | total_timesteps | 6430720 | | train/ | | | approx_kl | 0.039829828 | | clip_fraction | 0.205 | | clip_range | 0.142 | | entropy_loss | -5.04 | | explained_variance | 0.983 | | learning_rate | 0.000234 | | loss | -0.0198 | | n_updates | 3136 | | policy_gradient_loss | -0.0146 | | value_loss | 0.000117 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 50 | | ep_rew_mean | 0.842 | | time/ | | | fps | 1125 | | iterations | 786 | | time_elapsed | 5718 | | total_timesteps | 6438912 | | train/ | | | approx_kl | 0.033817418 | | clip_fraction | 0.214 | | clip_range | 0.142 | | entropy_loss | -5.12 | | explained_variance | 0.984 | | learning_rate | 0.000234 | | loss | -0.0229 | | n_updates | 3140 | | policy_gradient_loss | -0.0159 | | value_loss | 0.000127 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 50.1 | | ep_rew_mean | 0.842 | | time/ | | | fps | 1125 | | iterations | 787 | | time_elapsed | 5726 | | total_timesteps | 6447104 | | train/ | | | approx_kl | 0.043065824 | | clip_fraction | 0.243 | | clip_range | 0.142 | | entropy_loss | -5.16 | | explained_variance | 0.979 | | learning_rate | 0.000234 | | loss | -0.0259 | | n_updates | 3144 | | policy_gradient_loss | -0.0193 | | value_loss | 0.000201 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 49.5 | | ep_rew_mean | 0.843 | | time/ | | | fps | 1125 | | iterations | 788 | | time_elapsed | 5733 | | total_timesteps | 6455296 | | train/ | | | approx_kl | 0.054211844 | | clip_fraction | 0.298 | | clip_range | 0.142 | | entropy_loss | -5.22 | | explained_variance | 0.965 | | learning_rate | 0.000234 | | loss | -0.032 | | n_updates | 3148 | | policy_gradient_loss | -0.021 | | value_loss | 0.000367 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 49.5 | | ep_rew_mean | 0.843 | | time/ | | | fps | 1125 | | iterations | 789 | | time_elapsed | 5741 | | total_timesteps | 6463488 | | train/ | | | approx_kl | 0.04307641 | | clip_fraction | 0.269 | | clip_range | 0.142 | | entropy_loss | -5.16 | | explained_variance | 0.953 | | learning_rate | 0.000234 | | loss | -0.0258 | | n_updates | 3152 | | policy_gradient_loss | -0.0167 | | value_loss | 0.000482 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 46 | | ep_rew_mean | 0.853 | | time/ | | | fps | 1125 | | iterations | 790 | | time_elapsed | 5748 | | total_timesteps | 6471680 | | train/ | | | approx_kl | 0.040333666 | | clip_fraction | 0.255 | | clip_range | 0.142 | | entropy_loss | -5.21 | | explained_variance | 0.98 | | learning_rate | 0.000234 | | loss | -0.0311 | | n_updates | 3156 | | policy_gradient_loss | -0.022 | | value_loss | 0.000211 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 46.2 | | ep_rew_mean | 0.854 | | time/ | | | fps | 1125 | | iterations | 791 | | time_elapsed | 5755 | | total_timesteps | 6479872 | | train/ | | | approx_kl | 0.028134856 | | clip_fraction | 0.203 | | clip_range | 0.142 | | entropy_loss | -5.09 | | explained_variance | 0.967 | | learning_rate | 0.000234 | | loss | -0.0185 | | n_updates | 3160 | | policy_gradient_loss | -0.0121 | | value_loss | 0.000229 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 48.6 | | ep_rew_mean | 0.841 | | time/ | | | fps | 1125 | | iterations | 792 | | time_elapsed | 5762 | | total_timesteps | 6488064 | | train/ | | | approx_kl | 0.017897256 | | clip_fraction | 0.21 | | clip_range | 0.142 | | entropy_loss | -5.02 | | explained_variance | 0.982 | | learning_rate | 0.000234 | | loss | -0.0104 | | n_updates | 3164 | | policy_gradient_loss | -0.00701 | | value_loss | 9.29e-05 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 47.2 | | ep_rew_mean | 0.852 | | time/ | | | fps | 1125 | | iterations | 793 | | time_elapsed | 5770 | | total_timesteps | 6496256 | | train/ | | | approx_kl | 0.037010256 | | clip_fraction | 0.26 | | clip_range | 0.142 | | entropy_loss | -5.13 | | explained_variance | 0.965 | | learning_rate | 0.000234 | | loss | -0.0201 | | n_updates | 3168 | | policy_gradient_loss | -0.0148 | | value_loss | 0.000249 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 47.3 | | ep_rew_mean | 0.851 | | time/ | | | fps | 1125 | | iterations | 794 | | time_elapsed | 5777 | | total_timesteps | 6504448 | | train/ | | | approx_kl | 0.029477585 | | clip_fraction | 0.176 | | clip_range | 0.142 | | entropy_loss | -5.09 | | explained_variance | 0.955 | | learning_rate | 0.000234 | | loss | -0.0196 | | n_updates | 3172 | | policy_gradient_loss | -0.0125 | | value_loss | 0.000219 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 48.6 | | ep_rew_mean | 0.849 | | time/ | | | fps | 1125 | | iterations | 795 | | time_elapsed | 5785 | | total_timesteps | 6512640 | | train/ | | | approx_kl | 0.03641277 | | clip_fraction | 0.221 | | clip_range | 0.142 | | entropy_loss | -5.06 | | explained_variance | 0.974 | | learning_rate | 0.000234 | | loss | -0.0161 | | n_updates | 3176 | | policy_gradient_loss | -0.011 | | value_loss | 0.000158 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 48.8 | | ep_rew_mean | 0.841 | | time/ | | | fps | 1125 | | iterations | 796 | | time_elapsed | 5792 | | total_timesteps | 6520832 | | train/ | | | approx_kl | 0.03163231 | | clip_fraction | 0.245 | | clip_range | 0.142 | | entropy_loss | -5.12 | | explained_variance | 0.952 | | learning_rate | 0.000234 | | loss | -0.0218 | | n_updates | 3180 | | policy_gradient_loss | -0.0161 | | value_loss | 0.000349 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 50.3 | | ep_rew_mean | 0.843 | | time/ | | | fps | 1125 | | iterations | 797 | | time_elapsed | 5800 | | total_timesteps | 6529024 | | train/ | | | approx_kl | 0.03802508 | | clip_fraction | 0.235 | | clip_range | 0.142 | | entropy_loss | -5.11 | | explained_variance | 0.979 | | learning_rate | 0.000234 | | loss | -0.0209 | | n_updates | 3184 | | policy_gradient_loss | -0.0189 | | value_loss | 0.000181 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 49.4 | | ep_rew_mean | 0.842 | | time/ | | | fps | 1125 | | iterations | 798 | | time_elapsed | 5807 | | total_timesteps | 6537216 | | train/ | | | approx_kl | 0.055112638 | | clip_fraction | 0.235 | | clip_range | 0.142 | | entropy_loss | -5.19 | | explained_variance | 0.974 | | learning_rate | 0.000234 | | loss | -0.0309 | | n_updates | 3188 | | policy_gradient_loss | -0.0199 | | value_loss | 0.000222 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 46.8 | | ep_rew_mean | 0.843 | | time/ | | | fps | 1125 | | iterations | 799 | | time_elapsed | 5814 | | total_timesteps | 6545408 | | train/ | | | approx_kl | 0.040802427 | | clip_fraction | 0.258 | | clip_range | 0.142 | | entropy_loss | -5.14 | | explained_variance | 0.969 | | learning_rate | 0.000234 | | loss | -0.0207 | | n_updates | 3192 | | policy_gradient_loss | -0.0169 | | value_loss | 0.00024 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 46 | | ep_rew_mean | 0.853 | | time/ | | | fps | 1125 | | iterations | 800 | | time_elapsed | 5821 | | total_timesteps | 6553600 | | train/ | | | approx_kl | 0.02460128 | | clip_fraction | 0.225 | | clip_range | 0.142 | | entropy_loss | -5.05 | | explained_variance | 0.986 | | learning_rate | 0.000234 | | loss | -0.0153 | | n_updates | 3196 | | policy_gradient_loss | -0.0102 | | value_loss | 0.000104 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 46 | | ep_rew_mean | 0.853 | | time/ | | | fps | 1125 | | iterations | 801 | | time_elapsed | 5829 | | total_timesteps | 6561792 | | train/ | | | approx_kl | 0.030457243 | | clip_fraction | 0.196 | | clip_range | 0.142 | | entropy_loss | -5.02 | | explained_variance | 0.995 | | learning_rate | 0.000234 | | loss | -0.0201 | | n_updates | 3200 | | policy_gradient_loss | -0.00937 | | value_loss | 4.1e-05 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 54.3 | | ep_rew_mean | 0.835 | | time/ | | | fps | 1125 | | iterations | 802 | | time_elapsed | 5836 | | total_timesteps | 6569984 | | train/ | | | approx_kl | 0.012211589 | | clip_fraction | 0.227 | | clip_range | 0.142 | | entropy_loss | -5.01 | | explained_variance | 0.977 | | learning_rate | 0.000234 | | loss | 0.0199 | | n_updates | 3204 | | policy_gradient_loss | -0.00474 | | value_loss | 0.000147 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 48 | | ep_rew_mean | 0.851 | | time/ | | | fps | 1125 | | iterations | 803 | | time_elapsed | 5843 | | total_timesteps | 6578176 | | train/ | | | approx_kl | 0.061349977 | | clip_fraction | 0.315 | | clip_range | 0.142 | | entropy_loss | -5.28 | | explained_variance | 0.932 | | learning_rate | 0.000234 | | loss | -0.0326 | | n_updates | 3208 | | policy_gradient_loss | -0.0205 | | value_loss | 0.000833 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 47.9 | | ep_rew_mean | 0.847 | | time/ | | | fps | 1125 | | iterations | 804 | | time_elapsed | 5851 | | total_timesteps | 6586368 | | train/ | | | approx_kl | 0.04115832 | | clip_fraction | 0.23 | | clip_range | 0.142 | | entropy_loss | -5.07 | | explained_variance | 0.965 | | learning_rate | 0.000234 | | loss | -0.0191 | | n_updates | 3212 | | policy_gradient_loss | -0.0143 | | value_loss | 0.000229 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 47.7 | | ep_rew_mean | 0.847 | | time/ | | | fps | 1125 | | iterations | 805 | | time_elapsed | 5858 | | total_timesteps | 6594560 | | train/ | | | approx_kl | 0.032970298 | | clip_fraction | 0.226 | | clip_range | 0.142 | | entropy_loss | -5.03 | | explained_variance | 0.973 | | learning_rate | 0.000234 | | loss | -0.0204 | | n_updates | 3216 | | policy_gradient_loss | -0.0133 | | value_loss | 0.000204 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 46 | | ep_rew_mean | 0.853 | | time/ | | | fps | 1125 | | iterations | 806 | | time_elapsed | 5866 | | total_timesteps | 6602752 | | train/ | | | approx_kl | 0.03360557 | | clip_fraction | 0.209 | | clip_range | 0.142 | | entropy_loss | -4.98 | | explained_variance | 0.984 | | learning_rate | 0.000234 | | loss | -0.0125 | | n_updates | 3220 | | policy_gradient_loss | -0.0117 | | value_loss | 0.000111 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 46.9 | | ep_rew_mean | 0.846 | | time/ | | | fps | 1125 | | iterations | 807 | | time_elapsed | 5873 | | total_timesteps | 6610944 | | train/ | | | approx_kl | 0.015501356 | | clip_fraction | 0.218 | | clip_range | 0.142 | | entropy_loss | -4.98 | | explained_variance | 0.985 | | learning_rate | 0.000234 | | loss | -0.0081 | | n_updates | 3224 | | policy_gradient_loss | -0.00752 | | value_loss | 8.94e-05 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 48.2 | | ep_rew_mean | 0.846 | | time/ | | | fps | 1125 | | iterations | 808 | | time_elapsed | 5880 | | total_timesteps | 6619136 | | train/ | | | approx_kl | 0.020969227 | | clip_fraction | 0.234 | | clip_range | 0.142 | | entropy_loss | -5.04 | | explained_variance | 0.977 | | learning_rate | 0.000234 | | loss | -0.0154 | | n_updates | 3228 | | policy_gradient_loss | -0.00933 | | value_loss | 0.000155 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 46 | | ep_rew_mean | 0.853 | | time/ | | | fps | 1125 | | iterations | 809 | | time_elapsed | 5888 | | total_timesteps | 6627328 | | train/ | | | approx_kl | 0.04721541 | | clip_fraction | 0.213 | | clip_range | 0.142 | | entropy_loss | -5.04 | | explained_variance | 0.964 | | learning_rate | 0.000234 | | loss | -0.0179 | | n_updates | 3232 | | policy_gradient_loss | -0.0113 | | value_loss | 0.000254 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 46 | | ep_rew_mean | 0.853 | | time/ | | | fps | 1125 | | iterations | 810 | | time_elapsed | 5895 | | total_timesteps | 6635520 | | train/ | | | approx_kl | 0.025107604 | | clip_fraction | 0.205 | | clip_range | 0.142 | | entropy_loss | -5.02 | | explained_variance | 0.983 | | learning_rate | 0.000234 | | loss | -0.00671 | | n_updates | 3236 | | policy_gradient_loss | -0.01 | | value_loss | 0.000109 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 46.6 | | ep_rew_mean | 0.853 | | time/ | | | fps | 1125 | | iterations | 811 | | time_elapsed | 5902 | | total_timesteps | 6643712 | | train/ | | | approx_kl | 0.022637725 | | clip_fraction | 0.213 | | clip_range | 0.142 | | entropy_loss | -4.98 | | explained_variance | 0.98 | | learning_rate | 0.000234 | | loss | -0.0151 | | n_updates | 3240 | | policy_gradient_loss | -0.0105 | | value_loss | 0.000126 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 47.8 | | ep_rew_mean | 0.847 | | time/ | | | fps | 1125 | | iterations | 812 | | time_elapsed | 5910 | | total_timesteps | 6651904 | | train/ | | | approx_kl | 0.028323751 | | clip_fraction | 0.223 | | clip_range | 0.142 | | entropy_loss | -5.07 | | explained_variance | 0.969 | | learning_rate | 0.000234 | | loss | -0.0182 | | n_updates | 3244 | | policy_gradient_loss | -0.0133 | | value_loss | 0.000225 | ----------------------------------------- -------------------------------------- | rollout/ | | | ep_len_mean | 47.5 | | ep_rew_mean | 0.843 | | time/ | | | fps | 1125 | | iterations | 813 | | time_elapsed | 5917 | | total_timesteps | 6660096 | | train/ | | | approx_kl | 0.034639 | | clip_fraction | 0.216 | | clip_range | 0.142 | | entropy_loss | -5.08 | | explained_variance | 0.977 | | learning_rate | 0.000234 | | loss | -0.0121 | | n_updates | 3248 | | policy_gradient_loss | -0.012 | | value_loss | 0.000176 | -------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 47.1 | | ep_rew_mean | 0.851 | | time/ | | | fps | 1125 | | iterations | 814 | | time_elapsed | 5924 | | total_timesteps | 6668288 | | train/ | | | approx_kl | 0.059522096 | | clip_fraction | 0.22 | | clip_range | 0.142 | | entropy_loss | -5.13 | | explained_variance | 0.96 | | learning_rate | 0.000234 | | loss | -0.0212 | | n_updates | 3252 | | policy_gradient_loss | -0.0142 | | value_loss | 0.000314 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 47.4 | | ep_rew_mean | 0.851 | | time/ | | | fps | 1125 | | iterations | 815 | | time_elapsed | 5931 | | total_timesteps | 6676480 | | train/ | | | approx_kl | 0.04286322 | | clip_fraction | 0.236 | | clip_range | 0.142 | | entropy_loss | -5.16 | | explained_variance | 0.965 | | learning_rate | 0.000233 | | loss | -0.0209 | | n_updates | 3256 | | policy_gradient_loss | -0.0155 | | value_loss | 0.000274 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 46 | | ep_rew_mean | 0.853 | | time/ | | | fps | 1125 | | iterations | 816 | | time_elapsed | 5938 | | total_timesteps | 6684672 | | train/ | | | approx_kl | 0.037303083 | | clip_fraction | 0.226 | | clip_range | 0.142 | | entropy_loss | -5.09 | | explained_variance | 0.967 | | learning_rate | 0.000233 | | loss | -0.0112 | | n_updates | 3260 | | policy_gradient_loss | -0.0129 | | value_loss | 0.000205 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 47.8 | | ep_rew_mean | 0.845 | | time/ | | | fps | 1125 | | iterations | 817 | | time_elapsed | 5946 | | total_timesteps | 6692864 | | train/ | | | approx_kl | 0.015058521 | | clip_fraction | 0.17 | | clip_range | 0.142 | | entropy_loss | -5.06 | | explained_variance | 0.987 | | learning_rate | 0.000233 | | loss | -0.0132 | | n_updates | 3264 | | policy_gradient_loss | -0.00847 | | value_loss | 7.98e-05 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 46 | | ep_rew_mean | 0.853 | | time/ | | | fps | 1125 | | iterations | 818 | | time_elapsed | 5953 | | total_timesteps | 6701056 | | train/ | | | approx_kl | 0.022279281 | | clip_fraction | 0.202 | | clip_range | 0.142 | | entropy_loss | -5.14 | | explained_variance | 0.986 | | learning_rate | 0.000233 | | loss | -0.0151 | | n_updates | 3268 | | policy_gradient_loss | -0.011 | | value_loss | 9.2e-05 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 47.6 | | ep_rew_mean | 0.85 | | time/ | | | fps | 1125 | | iterations | 819 | | time_elapsed | 5961 | | total_timesteps | 6709248 | | train/ | | | approx_kl | 0.026741974 | | clip_fraction | 0.244 | | clip_range | 0.142 | | entropy_loss | -5.15 | | explained_variance | 0.946 | | learning_rate | 0.000233 | | loss | -0.0232 | | n_updates | 3272 | | policy_gradient_loss | -0.0119 | | value_loss | 0.000403 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 47.1 | | ep_rew_mean | 0.842 | | time/ | | | fps | 1125 | | iterations | 820 | | time_elapsed | 5968 | | total_timesteps | 6717440 | | train/ | | | approx_kl | 0.03894692 | | clip_fraction | 0.199 | | clip_range | 0.142 | | entropy_loss | -5.2 | | explained_variance | 0.954 | | learning_rate | 0.000233 | | loss | -0.021 | | n_updates | 3276 | | policy_gradient_loss | -0.0155 | | value_loss | 0.000335 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 48.5 | | ep_rew_mean | 0.842 | | time/ | | | fps | 1125 | | iterations | 821 | | time_elapsed | 5976 | | total_timesteps | 6725632 | | train/ | | | approx_kl | 0.032750554 | | clip_fraction | 0.212 | | clip_range | 0.142 | | entropy_loss | -5.14 | | explained_variance | 0.973 | | learning_rate | 0.000233 | | loss | -0.0153 | | n_updates | 3280 | | policy_gradient_loss | -0.0161 | | value_loss | 0.000188 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 48.5 | | ep_rew_mean | 0.847 | | time/ | | | fps | 1125 | | iterations | 822 | | time_elapsed | 5983 | | total_timesteps | 6733824 | | train/ | | | approx_kl | 0.046135433 | | clip_fraction | 0.207 | | clip_range | 0.142 | | entropy_loss | -5.11 | | explained_variance | 0.969 | | learning_rate | 0.000233 | | loss | -0.0157 | | n_updates | 3284 | | policy_gradient_loss | -0.0143 | | value_loss | 0.000223 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 46 | | ep_rew_mean | 0.853 | | time/ | | | fps | 1125 | | iterations | 823 | | time_elapsed | 5990 | | total_timesteps | 6742016 | | train/ | | | approx_kl | 0.02728849 | | clip_fraction | 0.199 | | clip_range | 0.142 | | entropy_loss | -5.12 | | explained_variance | 0.99 | | learning_rate | 0.000233 | | loss | -0.021 | | n_updates | 3288 | | policy_gradient_loss | -0.0125 | | value_loss | 7.42e-05 | ---------------------------------------- ------------------------------------------ | rollout/ | | | ep_len_mean | 46.5 | | ep_rew_mean | 0.854 | | time/ | | | fps | 1125 | | iterations | 824 | | time_elapsed | 5998 | | total_timesteps | 6750208 | | train/ | | | approx_kl | 0.0128123695 | | clip_fraction | 0.218 | | clip_range | 0.142 | | entropy_loss | -5.07 | | explained_variance | 0.99 | | learning_rate | 0.000233 | | loss | -0.000859 | | n_updates | 3292 | | policy_gradient_loss | -0.00815 | | value_loss | 7.19e-05 | ------------------------------------------ ----------------------------------------- | rollout/ | | | ep_len_mean | 47.2 | | ep_rew_mean | 0.852 | | time/ | | | fps | 1125 | | iterations | 825 | | time_elapsed | 6006 | | total_timesteps | 6758400 | | train/ | | | approx_kl | 0.028587349 | | clip_fraction | 0.229 | | clip_range | 0.142 | | entropy_loss | -5.11 | | explained_variance | 0.965 | | learning_rate | 0.000233 | | loss | -0.0128 | | n_updates | 3296 | | policy_gradient_loss | -0.0119 | | value_loss | 0.000237 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 47.1 | | ep_rew_mean | 0.848 | | time/ | | | fps | 1125 | | iterations | 826 | | time_elapsed | 6013 | | total_timesteps | 6766592 | | train/ | | | approx_kl | 0.04846013 | | clip_fraction | 0.245 | | clip_range | 0.142 | | entropy_loss | -5.2 | | explained_variance | 0.956 | | learning_rate | 0.000233 | | loss | -0.0204 | | n_updates | 3300 | | policy_gradient_loss | -0.0149 | | value_loss | 0.000328 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 52.7 | | ep_rew_mean | 0.837 | | time/ | | | fps | 1125 | | iterations | 827 | | time_elapsed | 6020 | | total_timesteps | 6774784 | | train/ | | | approx_kl | 0.019571748 | | clip_fraction | 0.218 | | clip_range | 0.142 | | entropy_loss | -5.13 | | explained_variance | 0.975 | | learning_rate | 0.000233 | | loss | -0.00798 | | n_updates | 3304 | | policy_gradient_loss | -0.0118 | | value_loss | 0.000164 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 50.2 | | ep_rew_mean | 0.844 | | time/ | | | fps | 1125 | | iterations | 828 | | time_elapsed | 6027 | | total_timesteps | 6782976 | | train/ | | | approx_kl | 0.04891327 | | clip_fraction | 0.251 | | clip_range | 0.142 | | entropy_loss | -5.3 | | explained_variance | 0.973 | | learning_rate | 0.000233 | | loss | -0.0356 | | n_updates | 3308 | | policy_gradient_loss | -0.0208 | | value_loss | 0.000263 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 47.7 | | ep_rew_mean | 0.847 | | time/ | | | fps | 1125 | | iterations | 829 | | time_elapsed | 6035 | | total_timesteps | 6791168 | | train/ | | | approx_kl | 0.037181236 | | clip_fraction | 0.24 | | clip_range | 0.142 | | entropy_loss | -5.26 | | explained_variance | 0.96 | | learning_rate | 0.000233 | | loss | -0.025 | | n_updates | 3312 | | policy_gradient_loss | -0.019 | | value_loss | 0.000352 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 49.3 | | ep_rew_mean | 0.837 | | time/ | | | fps | 1125 | | iterations | 830 | | time_elapsed | 6042 | | total_timesteps | 6799360 | | train/ | | | approx_kl | 0.023251036 | | clip_fraction | 0.22 | | clip_range | 0.142 | | entropy_loss | -5.2 | | explained_variance | 0.978 | | learning_rate | 0.000233 | | loss | -0.0237 | | n_updates | 3316 | | policy_gradient_loss | -0.0129 | | value_loss | 0.00015 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 46.9 | | ep_rew_mean | 0.854 | | time/ | | | fps | 1125 | | iterations | 831 | | time_elapsed | 6049 | | total_timesteps | 6807552 | | train/ | | | approx_kl | 0.04387694 | | clip_fraction | 0.235 | | clip_range | 0.142 | | entropy_loss | -5.29 | | explained_variance | 0.974 | | learning_rate | 0.000233 | | loss | -0.0195 | | n_updates | 3320 | | policy_gradient_loss | -0.0158 | | value_loss | 0.000222 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 46 | | ep_rew_mean | 0.853 | | time/ | | | fps | 1125 | | iterations | 832 | | time_elapsed | 6056 | | total_timesteps | 6815744 | | train/ | | | approx_kl | 0.024846584 | | clip_fraction | 0.193 | | clip_range | 0.141 | | entropy_loss | -5.1 | | explained_variance | 0.945 | | learning_rate | 0.000233 | | loss | -0.0138 | | n_updates | 3324 | | policy_gradient_loss | -0.00831 | | value_loss | 0.000306 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 49.2 | | ep_rew_mean | 0.845 | | time/ | | | fps | 1125 | | iterations | 833 | | time_elapsed | 6064 | | total_timesteps | 6823936 | | train/ | | | approx_kl | 0.02767839 | | clip_fraction | 0.229 | | clip_range | 0.141 | | entropy_loss | -5.22 | | explained_variance | 0.976 | | learning_rate | 0.000233 | | loss | -0.0182 | | n_updates | 3328 | | policy_gradient_loss | -0.0141 | | value_loss | 0.000175 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 47.8 | | ep_rew_mean | 0.848 | | time/ | | | fps | 1125 | | iterations | 834 | | time_elapsed | 6071 | | total_timesteps | 6832128 | | train/ | | | approx_kl | 0.034100402 | | clip_fraction | 0.221 | | clip_range | 0.141 | | entropy_loss | -5.26 | | explained_variance | 0.973 | | learning_rate | 0.000233 | | loss | -0.0238 | | n_updates | 3332 | | policy_gradient_loss | -0.017 | | value_loss | 0.000236 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 47.9 | | ep_rew_mean | 0.849 | | time/ | | | fps | 1125 | | iterations | 835 | | time_elapsed | 6078 | | total_timesteps | 6840320 | | train/ | | | approx_kl | 0.029370539 | | clip_fraction | 0.2 | | clip_range | 0.141 | | entropy_loss | -5.25 | | explained_variance | 0.982 | | learning_rate | 0.000233 | | loss | -0.0224 | | n_updates | 3336 | | policy_gradient_loss | -0.0155 | | value_loss | 0.000149 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 46.2 | | ep_rew_mean | 0.854 | | time/ | | | fps | 1125 | | iterations | 836 | | time_elapsed | 6086 | | total_timesteps | 6848512 | | train/ | | | approx_kl | 0.022283178 | | clip_fraction | 0.197 | | clip_range | 0.141 | | entropy_loss | -5.2 | | explained_variance | 0.974 | | learning_rate | 0.000233 | | loss | -0.00426 | | n_updates | 3340 | | policy_gradient_loss | -0.00999 | | value_loss | 0.000174 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 47.5 | | ep_rew_mean | 0.847 | | time/ | | | fps | 1125 | | iterations | 837 | | time_elapsed | 6093 | | total_timesteps | 6856704 | | train/ | | | approx_kl | 0.016606688 | | clip_fraction | 0.202 | | clip_range | 0.141 | | entropy_loss | -5.17 | | explained_variance | 0.968 | | learning_rate | 0.000233 | | loss | -0.00984 | | n_updates | 3344 | | policy_gradient_loss | -0.00688 | | value_loss | 0.000169 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 50 | | ep_rew_mean | 0.843 | | time/ | | | fps | 1125 | | iterations | 838 | | time_elapsed | 6100 | | total_timesteps | 6864896 | | train/ | | | approx_kl | 0.032574862 | | clip_fraction | 0.177 | | clip_range | 0.141 | | entropy_loss | -5.28 | | explained_variance | 0.989 | | learning_rate | 0.000233 | | loss | -0.0193 | | n_updates | 3348 | | policy_gradient_loss | -0.0152 | | value_loss | 9.98e-05 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 46 | | ep_rew_mean | 0.853 | | time/ | | | fps | 1125 | | iterations | 839 | | time_elapsed | 6108 | | total_timesteps | 6873088 | | train/ | | | approx_kl | 0.04932686 | | clip_fraction | 0.239 | | clip_range | 0.141 | | entropy_loss | -5.29 | | explained_variance | 0.971 | | learning_rate | 0.000233 | | loss | -0.0257 | | n_updates | 3352 | | policy_gradient_loss | -0.019 | | value_loss | 0.000249 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 46 | | ep_rew_mean | 0.853 | | time/ | | | fps | 1125 | | iterations | 840 | | time_elapsed | 6115 | | total_timesteps | 6881280 | | train/ | | | approx_kl | 0.02459896 | | clip_fraction | 0.183 | | clip_range | 0.141 | | entropy_loss | -5.2 | | explained_variance | 0.988 | | learning_rate | 0.000233 | | loss | -0.0193 | | n_updates | 3356 | | policy_gradient_loss | -0.0106 | | value_loss | 7.9e-05 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 48 | | ep_rew_mean | 0.849 | | time/ | | | fps | 1125 | | iterations | 841 | | time_elapsed | 6122 | | total_timesteps | 6889472 | | train/ | | | approx_kl | 0.024406128 | | clip_fraction | 0.166 | | clip_range | 0.141 | | entropy_loss | -5.14 | | explained_variance | 0.984 | | learning_rate | 0.000233 | | loss | -0.0158 | | n_updates | 3360 | | policy_gradient_loss | -0.00626 | | value_loss | 7.64e-05 | ----------------------------------------- --------------------------------------- | rollout/ | | | ep_len_mean | 46.2 | | ep_rew_mean | 0.854 | | time/ | | | fps | 1125 | | iterations | 842 | | time_elapsed | 6130 | | total_timesteps | 6897664 | | train/ | | | approx_kl | 0.0415909 | | clip_fraction | 0.22 | | clip_range | 0.141 | | entropy_loss | -5.16 | | explained_variance | 0.944 | | learning_rate | 0.000233 | | loss | -0.0205 | | n_updates | 3364 | | policy_gradient_loss | -0.0127 | | value_loss | 0.000358 | --------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 47.4 | | ep_rew_mean | 0.846 | | time/ | | | fps | 1125 | | iterations | 843 | | time_elapsed | 6137 | | total_timesteps | 6905856 | | train/ | | | approx_kl | 0.020347431 | | clip_fraction | 0.221 | | clip_range | 0.141 | | entropy_loss | -5.14 | | explained_variance | 0.982 | | learning_rate | 0.000233 | | loss | -0.0211 | | n_updates | 3368 | | policy_gradient_loss | -0.00986 | | value_loss | 0.000117 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 46 | | ep_rew_mean | 0.853 | | time/ | | | fps | 1125 | | iterations | 844 | | time_elapsed | 6144 | | total_timesteps | 6914048 | | train/ | | | approx_kl | 0.028655581 | | clip_fraction | 0.204 | | clip_range | 0.141 | | entropy_loss | -5.18 | | explained_variance | 0.977 | | learning_rate | 0.000233 | | loss | -0.0214 | | n_updates | 3372 | | policy_gradient_loss | -0.0133 | | value_loss | 0.000173 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 47.4 | | ep_rew_mean | 0.847 | | time/ | | | fps | 1125 | | iterations | 845 | | time_elapsed | 6152 | | total_timesteps | 6922240 | | train/ | | | approx_kl | 0.024476504 | | clip_fraction | 0.231 | | clip_range | 0.141 | | entropy_loss | -5.16 | | explained_variance | 0.979 | | learning_rate | 0.000233 | | loss | -0.0149 | | n_updates | 3376 | | policy_gradient_loss | -0.0117 | | value_loss | 0.000157 | ----------------------------------------- --------------------------------------- | rollout/ | | | ep_len_mean | 51.2 | | ep_rew_mean | 0.839 | | time/ | | | fps | 1125 | | iterations | 846 | | time_elapsed | 6159 | | total_timesteps | 6930432 | | train/ | | | approx_kl | 0.0510982 | | clip_fraction | 0.198 | | clip_range | 0.141 | | entropy_loss | -5.21 | | explained_variance | 0.981 | | learning_rate | 0.000233 | | loss | -0.017 | | n_updates | 3380 | | policy_gradient_loss | -0.0156 | | value_loss | 0.000148 | --------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 48.3 | | ep_rew_mean | 0.848 | | time/ | | | fps | 1125 | | iterations | 847 | | time_elapsed | 6167 | | total_timesteps | 6938624 | | train/ | | | approx_kl | 0.042876672 | | clip_fraction | 0.218 | | clip_range | 0.141 | | entropy_loss | -5.29 | | explained_variance | 0.975 | | learning_rate | 0.000233 | | loss | -0.0265 | | n_updates | 3384 | | policy_gradient_loss | -0.0196 | | value_loss | 0.000224 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 47.1 | | ep_rew_mean | 0.848 | | time/ | | | fps | 1125 | | iterations | 848 | | time_elapsed | 6174 | | total_timesteps | 6946816 | | train/ | | | approx_kl | 0.034393117 | | clip_fraction | 0.214 | | clip_range | 0.141 | | entropy_loss | -5.2 | | explained_variance | 0.981 | | learning_rate | 0.000233 | | loss | -0.0174 | | n_updates | 3388 | | policy_gradient_loss | -0.0148 | | value_loss | 0.000137 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 49.2 | | ep_rew_mean | 0.847 | | time/ | | | fps | 1125 | | iterations | 849 | | time_elapsed | 6182 | | total_timesteps | 6955008 | | train/ | | | approx_kl | 0.029551372 | | clip_fraction | 0.193 | | clip_range | 0.141 | | entropy_loss | -5.21 | | explained_variance | 0.986 | | learning_rate | 0.000233 | | loss | -0.0152 | | n_updates | 3392 | | policy_gradient_loss | -0.0108 | | value_loss | 0.000109 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 48.2 | | ep_rew_mean | 0.848 | | time/ | | | fps | 1125 | | iterations | 850 | | time_elapsed | 6189 | | total_timesteps | 6963200 | | train/ | | | approx_kl | 0.03489526 | | clip_fraction | 0.269 | | clip_range | 0.141 | | entropy_loss | -5.38 | | explained_variance | 0.938 | | learning_rate | 0.000233 | | loss | -0.033 | | n_updates | 3396 | | policy_gradient_loss | -0.0209 | | value_loss | 0.000606 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 47.9 | | ep_rew_mean | 0.851 | | time/ | | | fps | 1125 | | iterations | 851 | | time_elapsed | 6196 | | total_timesteps | 6971392 | | train/ | | | approx_kl | 0.043191776 | | clip_fraction | 0.202 | | clip_range | 0.141 | | entropy_loss | -5.27 | | explained_variance | 0.964 | | learning_rate | 0.000233 | | loss | -0.0216 | | n_updates | 3400 | | policy_gradient_loss | -0.0155 | | value_loss | 0.000294 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 46 | | ep_rew_mean | 0.853 | | time/ | | | fps | 1125 | | iterations | 852 | | time_elapsed | 6203 | | total_timesteps | 6979584 | | train/ | | | approx_kl | 0.033072513 | | clip_fraction | 0.255 | | clip_range | 0.141 | | entropy_loss | -5.22 | | explained_variance | 0.966 | | learning_rate | 0.000233 | | loss | -0.0125 | | n_updates | 3404 | | policy_gradient_loss | -0.0134 | | value_loss | 0.000289 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 46 | | ep_rew_mean | 0.853 | | time/ | | | fps | 1125 | | iterations | 853 | | time_elapsed | 6211 | | total_timesteps | 6987776 | | train/ | | | approx_kl | 0.02262435 | | clip_fraction | 0.155 | | clip_range | 0.141 | | entropy_loss | -5.28 | | explained_variance | 0.976 | | learning_rate | 0.000233 | | loss | -0.00991 | | n_updates | 3408 | | policy_gradient_loss | -0.00966 | | value_loss | 0.000126 | ---------------------------------------- ------------------------------------------ | rollout/ | | | ep_len_mean | 51.9 | | ep_rew_mean | 0.839 | | time/ | | | fps | 1124 | | iterations | 854 | | time_elapsed | 6218 | | total_timesteps | 6995968 | | train/ | | | approx_kl | 0.0075386907 | | clip_fraction | 0.156 | | clip_range | 0.141 | | entropy_loss | -5.25 | | explained_variance | 0.985 | | learning_rate | 0.000233 | | loss | -0.0128 | | n_updates | 3412 | | policy_gradient_loss | -0.00369 | | value_loss | 8.72e-05 | ------------------------------------------ ----------------------------------------- | rollout/ | | | ep_len_mean | 50.9 | | ep_rew_mean | 0.843 | | time/ | | | fps | 1124 | | iterations | 855 | | time_elapsed | 6226 | | total_timesteps | 7004160 | | train/ | | | approx_kl | 0.032338783 | | clip_fraction | 0.221 | | clip_range | 0.141 | | entropy_loss | -5.34 | | explained_variance | 0.966 | | learning_rate | 0.000233 | | loss | -0.0275 | | n_updates | 3416 | | policy_gradient_loss | -0.0184 | | value_loss | 0.000282 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 49.7 | | ep_rew_mean | 0.847 | | time/ | | | fps | 1124 | | iterations | 856 | | time_elapsed | 6233 | | total_timesteps | 7012352 | | train/ | | | approx_kl | 0.03896132 | | clip_fraction | 0.227 | | clip_range | 0.141 | | entropy_loss | -5.34 | | explained_variance | 0.942 | | learning_rate | 0.000233 | | loss | -0.0208 | | n_updates | 3420 | | policy_gradient_loss | -0.0177 | | value_loss | 0.000486 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 48.6 | | ep_rew_mean | 0.85 | | time/ | | | fps | 1124 | | iterations | 857 | | time_elapsed | 6240 | | total_timesteps | 7020544 | | train/ | | | approx_kl | 0.036895618 | | clip_fraction | 0.186 | | clip_range | 0.141 | | entropy_loss | -5.27 | | explained_variance | 0.966 | | learning_rate | 0.000233 | | loss | -0.0182 | | n_updates | 3424 | | policy_gradient_loss | -0.016 | | value_loss | 0.000289 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 46 | | ep_rew_mean | 0.853 | | time/ | | | fps | 1124 | | iterations | 858 | | time_elapsed | 6247 | | total_timesteps | 7028736 | | train/ | | | approx_kl | 0.029945202 | | clip_fraction | 0.182 | | clip_range | 0.141 | | entropy_loss | -5.2 | | explained_variance | 0.987 | | learning_rate | 0.000233 | | loss | -0.0208 | | n_updates | 3428 | | policy_gradient_loss | -0.0144 | | value_loss | 0.000103 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 47.1 | | ep_rew_mean | 0.851 | | time/ | | | fps | 1124 | | iterations | 859 | | time_elapsed | 6255 | | total_timesteps | 7036928 | | train/ | | | approx_kl | 0.008434278 | | clip_fraction | 0.187 | | clip_range | 0.141 | | entropy_loss | -5.15 | | explained_variance | 0.998 | | learning_rate | 0.000233 | | loss | -0.0235 | | n_updates | 3432 | | policy_gradient_loss | -0.00704 | | value_loss | 3.02e-05 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 49.5 | | ep_rew_mean | 0.844 | | time/ | | | fps | 1124 | | iterations | 860 | | time_elapsed | 6262 | | total_timesteps | 7045120 | | train/ | | | approx_kl | 0.04286689 | | clip_fraction | 0.251 | | clip_range | 0.141 | | entropy_loss | -5.29 | | explained_variance | 0.963 | | learning_rate | 0.000233 | | loss | -0.0229 | | n_updates | 3436 | | policy_gradient_loss | -0.0181 | | value_loss | 0.000336 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 49 | | ep_rew_mean | 0.847 | | time/ | | | fps | 1124 | | iterations | 861 | | time_elapsed | 6270 | | total_timesteps | 7053312 | | train/ | | | approx_kl | 0.03362903 | | clip_fraction | 0.242 | | clip_range | 0.141 | | entropy_loss | -5.26 | | explained_variance | 0.967 | | learning_rate | 0.000233 | | loss | -0.0237 | | n_updates | 3440 | | policy_gradient_loss | -0.0187 | | value_loss | 0.000289 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 46 | | ep_rew_mean | 0.853 | | time/ | | | fps | 1124 | | iterations | 862 | | time_elapsed | 6277 | | total_timesteps | 7061504 | | train/ | | | approx_kl | 0.04660075 | | clip_fraction | 0.255 | | clip_range | 0.141 | | entropy_loss | -5.23 | | explained_variance | 0.956 | | learning_rate | 0.000233 | | loss | -0.0244 | | n_updates | 3444 | | policy_gradient_loss | -0.0161 | | value_loss | 0.000384 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 48.1 | | ep_rew_mean | 0.846 | | time/ | | | fps | 1124 | | iterations | 863 | | time_elapsed | 6284 | | total_timesteps | 7069696 | | train/ | | | approx_kl | 0.052064296 | | clip_fraction | 0.176 | | clip_range | 0.141 | | entropy_loss | -5.2 | | explained_variance | 0.982 | | learning_rate | 0.000233 | | loss | -0.021 | | n_updates | 3448 | | policy_gradient_loss | -0.015 | | value_loss | 0.000138 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 47.7 | | ep_rew_mean | 0.851 | | time/ | | | fps | 1124 | | iterations | 864 | | time_elapsed | 6291 | | total_timesteps | 7077888 | | train/ | | | approx_kl | 0.03355575 | | clip_fraction | 0.211 | | clip_range | 0.141 | | entropy_loss | -5.2 | | explained_variance | 0.981 | | learning_rate | 0.000233 | | loss | -0.0172 | | n_updates | 3452 | | policy_gradient_loss | -0.0139 | | value_loss | 0.000151 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 53.6 | | ep_rew_mean | 0.833 | | time/ | | | fps | 1124 | | iterations | 865 | | time_elapsed | 6298 | | total_timesteps | 7086080 | | train/ | | | approx_kl | 0.03970369 | | clip_fraction | 0.259 | | clip_range | 0.141 | | entropy_loss | -5.23 | | explained_variance | 0.973 | | learning_rate | 0.000232 | | loss | -0.0208 | | n_updates | 3456 | | policy_gradient_loss | -0.0155 | | value_loss | 0.000195 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 46.3 | | ep_rew_mean | 0.854 | | time/ | | | fps | 1124 | | iterations | 866 | | time_elapsed | 6306 | | total_timesteps | 7094272 | | train/ | | | approx_kl | 0.037389383 | | clip_fraction | 0.245 | | clip_range | 0.141 | | entropy_loss | -5.35 | | explained_variance | 0.961 | | learning_rate | 0.000232 | | loss | -0.0358 | | n_updates | 3460 | | policy_gradient_loss | -0.0204 | | value_loss | 0.000394 | ----------------------------------------- ------------------------------------------ | rollout/ | | | ep_len_mean | 46.3 | | ep_rew_mean | 0.854 | | time/ | | | fps | 1124 | | iterations | 867 | | time_elapsed | 6313 | | total_timesteps | 7102464 | | train/ | | | approx_kl | 0.0120342355 | | clip_fraction | 0.207 | | clip_range | 0.141 | | entropy_loss | -5.09 | | explained_variance | 0.981 | | learning_rate | 0.000232 | | loss | -0.00787 | | n_updates | 3464 | | policy_gradient_loss | -0.00701 | | value_loss | 0.000117 | ------------------------------------------ ---------------------------------------- | rollout/ | | | ep_len_mean | 52.2 | | ep_rew_mean | 0.84 | | time/ | | | fps | 1124 | | iterations | 868 | | time_elapsed | 6321 | | total_timesteps | 7110656 | | train/ | | | approx_kl | 0.01594349 | | clip_fraction | 0.205 | | clip_range | 0.141 | | entropy_loss | -5.1 | | explained_variance | 0.978 | | learning_rate | 0.000232 | | loss | -0.00746 | | n_updates | 3468 | | policy_gradient_loss | -0.0089 | | value_loss | 0.00013 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 47.6 | | ep_rew_mean | 0.851 | | time/ | | | fps | 1124 | | iterations | 869 | | time_elapsed | 6328 | | total_timesteps | 7118848 | | train/ | | | approx_kl | 0.04062698 | | clip_fraction | 0.245 | | clip_range | 0.141 | | entropy_loss | -5.25 | | explained_variance | 0.965 | | learning_rate | 0.000232 | | loss | -0.0281 | | n_updates | 3472 | | policy_gradient_loss | -0.0189 | | value_loss | 0.00035 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 46 | | ep_rew_mean | 0.853 | | time/ | | | fps | 1124 | | iterations | 870 | | time_elapsed | 6335 | | total_timesteps | 7127040 | | train/ | | | approx_kl | 0.028115515 | | clip_fraction | 0.213 | | clip_range | 0.141 | | entropy_loss | -5.13 | | explained_variance | 0.977 | | learning_rate | 0.000232 | | loss | -0.0226 | | n_updates | 3476 | | policy_gradient_loss | -0.0142 | | value_loss | 0.000159 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 46.9 | | ep_rew_mean | 0.851 | | time/ | | | fps | 1124 | | iterations | 871 | | time_elapsed | 6343 | | total_timesteps | 7135232 | | train/ | | | approx_kl | 0.01063107 | | clip_fraction | 0.192 | | clip_range | 0.141 | | entropy_loss | -5.08 | | explained_variance | 0.991 | | learning_rate | 0.000232 | | loss | -0.00917 | | n_updates | 3480 | | policy_gradient_loss | -0.00406 | | value_loss | 6.02e-05 | ---------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 46 | | ep_rew_mean | 0.853 | | time/ | | | fps | 1124 | | iterations | 872 | | time_elapsed | 6350 | | total_timesteps | 7143424 | | train/ | | | approx_kl | 0.02534625 | | clip_fraction | 0.225 | | clip_range | 0.141 | | entropy_loss | -5.11 | | explained_variance | 0.969 | | learning_rate | 0.000232 | | loss | -0.0158 | | n_updates | 3484 | | policy_gradient_loss | -0.0124 | | value_loss | 0.000218 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 46 | | ep_rew_mean | 0.853 | | time/ | | | fps | 1124 | | iterations | 873 | | time_elapsed | 6357 | | total_timesteps | 7151616 | | train/ | | | approx_kl | 0.008821163 | | clip_fraction | 0.184 | | clip_range | 0.141 | | entropy_loss | -5.02 | | explained_variance | 0.997 | | learning_rate | 0.000232 | | loss | -0.0122 | | n_updates | 3488 | | policy_gradient_loss | -0.00656 | | value_loss | 2.68e-05 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 49.2 | | ep_rew_mean | 0.849 | | time/ | | | fps | 1124 | | iterations | 874 | | time_elapsed | 6365 | | total_timesteps | 7159808 | | train/ | | | approx_kl | 0.008496272 | | clip_fraction | 0.193 | | clip_range | 0.141 | | entropy_loss | -5.04 | | explained_variance | 0.992 | | learning_rate | 0.000232 | | loss | -0.00815 | | n_updates | 3492 | | policy_gradient_loss | -0.00528 | | value_loss | 6.85e-05 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 48.6 | | ep_rew_mean | 0.849 | | time/ | | | fps | 1124 | | iterations | 875 | | time_elapsed | 6372 | | total_timesteps | 7168000 | | train/ | | | approx_kl | 0.025475107 | | clip_fraction | 0.235 | | clip_range | 0.141 | | entropy_loss | -5.16 | | explained_variance | 0.973 | | learning_rate | 0.000232 | | loss | -0.0183 | | n_updates | 3496 | | policy_gradient_loss | -0.0136 | | value_loss | 0.000193 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 53.1 | | ep_rew_mean | 0.838 | | time/ | | | fps | 1124 | | iterations | 876 | | time_elapsed | 6379 | | total_timesteps | 7176192 | | train/ | | | approx_kl | 0.028008547 | | clip_fraction | 0.233 | | clip_range | 0.141 | | entropy_loss | -5.16 | | explained_variance | 0.955 | | learning_rate | 0.000232 | | loss | -0.0215 | | n_updates | 3500 | | policy_gradient_loss | -0.0163 | | value_loss | 0.000325 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 48.1 | | ep_rew_mean | 0.847 | | time/ | | | fps | 1124 | | iterations | 877 | | time_elapsed | 6386 | | total_timesteps | 7184384 | | train/ | | | approx_kl | 0.045767725 | | clip_fraction | 0.224 | | clip_range | 0.141 | | entropy_loss | -5.29 | | explained_variance | 0.978 | | learning_rate | 0.000232 | | loss | -0.0338 | | n_updates | 3504 | | policy_gradient_loss | -0.0221 | | value_loss | 0.000205 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 46.7 | | ep_rew_mean | 0.852 | | time/ | | | fps | 1124 | | iterations | 878 | | time_elapsed | 6394 | | total_timesteps | 7192576 | | train/ | | | approx_kl | 0.027111448 | | clip_fraction | 0.179 | | clip_range | 0.141 | | entropy_loss | -5.08 | | explained_variance | 0.991 | | learning_rate | 0.000232 | | loss | -0.0194 | | n_updates | 3508 | | policy_gradient_loss | -0.013 | | value_loss | 7.57e-05 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 46 | | ep_rew_mean | 0.853 | | time/ | | | fps | 1124 | | iterations | 879 | | time_elapsed | 6401 | | total_timesteps | 7200768 | | train/ | | | approx_kl | 0.02790926 | | clip_fraction | 0.181 | | clip_range | 0.141 | | entropy_loss | -5.03 | | explained_variance | 0.963 | | learning_rate | 0.000232 | | loss | -0.0119 | | n_updates | 3512 | | policy_gradient_loss | -0.0115 | | value_loss | 0.000237 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 50.2 | | ep_rew_mean | 0.846 | | time/ | | | fps | 1124 | | iterations | 880 | | time_elapsed | 6409 | | total_timesteps | 7208960 | | train/ | | | approx_kl | 0.008467438 | | clip_fraction | 0.175 | | clip_range | 0.141 | | entropy_loss | -4.96 | | explained_variance | 0.997 | | learning_rate | 0.000232 | | loss | -0.00275 | | n_updates | 3516 | | policy_gradient_loss | -0.00521 | | value_loss | 3.07e-05 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 49.5 | | ep_rew_mean | 0.844 | | time/ | | | fps | 1124 | | iterations | 881 | | time_elapsed | 6416 | | total_timesteps | 7217152 | | train/ | | | approx_kl | 0.028228959 | | clip_fraction | 0.226 | | clip_range | 0.141 | | entropy_loss | -5.06 | | explained_variance | 0.961 | | learning_rate | 0.000232 | | loss | -0.0193 | | n_updates | 3520 | | policy_gradient_loss | -0.0149 | | value_loss | 0.000297 | ----------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 46.4 | | ep_rew_mean | 0.854 | | time/ | | | fps | 1124 | | iterations | 882 | | time_elapsed | 6424 | | total_timesteps | 7225344 | | train/ | | | approx_kl | 0.039644137 | | clip_fraction | 0.247 | | clip_range | 0.141 | | entropy_loss | -5.15 | | explained_variance | 0.956 | | learning_rate | 0.000232 | | loss | -0.0264 | | n_updates | 3524 | | policy_gradient_loss | -0.0176 | | value_loss | 0.000395 | ----------------------------------------- ---------------------------------------- | rollout/ | | | ep_len_mean | 46.2 | | ep_rew_mean | 0.854 | | time/ | | | fps | 1124 | | iterations | 883 | | time_elapsed | 6431 | | total_timesteps | 7233536 | | train/ | | | approx_kl | 0.03067332 | | clip_fraction | 0.214 | | clip_range | 0.141 | | entropy_loss | -5.07 | | explained_variance | 0.965 | | learning_rate | 0.000232 | | loss | -0.0226 | | n_updates | 3528 | | policy_gradient_loss | -0.0124 | | value_loss | 0.000221 | ---------------------------------------- ----------------------------------------- | rollout/ | | | ep_len_mean | 48.4 | | ep_rew_mean | 0.848 | | time/ | | | fps | 1124 | | iterations | 884 | | time_elapsed | 6439 | | total_timesteps | 7241728 | | train/ | | | approx_kl | 0.026549514 | | clip_fraction | 0.182 | | clip_range | 0.141 | | entropy_loss | -5.08 | | explained_variance | 0.988 | | learning_rate | 0.000232 | | loss | -0.011 | | n_updates | 3532 | | policy_gradient_loss | -0.0126 | | value_loss | 6.91e-05 | -----------------------------------------