CGAR: Critic Guided Action Redistribution in Reinforcement Leaning

2022 IEEE Conference on Games (CoG)(2022)

引用 0|浏览7
暂无评分
摘要
Training a game-playing reinforcement learning agent requires multiple interactions with the environment. Ignorant random exploration may cause a waste of time and resources. It's essential to alleviate such waste. As discussed in this paper, under the settings of the off-policy actor critic algorithms, we demonstrate that the critic can bring more expected discounted rewards than or at least equal to the actor. Thus, the Q value predicted by the critic is a better signal to redistribute the action originally sampled from the policy distribution predicted by the actor. This paper introduces the novel Critic Guided Action Redistribution (CGAR) algorithm and tests it on the OpenAI MuJoCo tasks. The experimental results demonstrate that our method improves the sample efficiency and achieves state-of-the-art performance. Our code can be found at https://github.com/tairanhuang/CGAR.
更多
查看译文
关键词
Reinforcement Learning,Soft actor-critic,MuJoCo tasks
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要