From 51e0127371b9b1607d5bfde42587ef8bd9d7a269 Mon Sep 17 00:00:00 2001 From: Nikita-Vesel0v Date: Wed, 15 May 2024 01:45:41 +0300 Subject: [PATCH] Update README.md --- README.md | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/README.md b/README.md index f77fc8c..1fd7ec9 100644 --- a/README.md +++ b/README.md @@ -1,6 +1,5 @@ # SFighterAI -[简体中文](README_CN.md) | English | [Español](README_ES.md) This project is an AI agent trained using deep reinforcement learning to beat the final boss in the game "Street Fighter II: Special Champion Edition". The AI agent makes decisions based solely on the game screen's RGB pixel values. In the provided save state, the agent achieves a 100% win rate in the first round of the final level (overfitting occurs, see the [Running Tests](#running-tests) section for discussion). @@ -97,4 +96,4 @@ Two papers that had a significant impact on this project: The valuable summary of the experience in setting hyperparameters for deep reinforcement learning models in fighting games in this paper was of great help to the training process of this project. [2] [Mitigating Cowardice for Reinforcement Learning](https://ieee-cog.org/2022/assets/papers/paper_111.pdf) -The "penalty decay" mechanism proposed in this paper effectively solved the "cowardice" problem (always avoiding opponents and not daring to even try attacking moves). \ No newline at end of file +The "penalty decay" mechanism proposed in this paper effectively solved the "cowardice" problem (always avoiding opponents and not daring to even try attacking moves).