Abstract:
Training a game-playing reinforcement learning agent requires multiple interactions with the environment. Ignorant random exploration may cause a waste of time and resour...Show MoreMetadata
Abstract:
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.
Published in: 2022 IEEE Conference on Games (CoG)
Date of Conference: 21-24 August 2022
Date Added to IEEE Xplore: 20 September 2022
ISBN Information: