Distributional Soft Actor-Critic: Off-Policy Reinforcement Learning for Addressing Value Estimation Errors

By Jingliang Duan, Yang Guan, Shengbo Eben Li, Yangang Ren, Qi Sun, Bo Cheng. IEEE Transactions on Neural Networks and Learning Systems, 2020

317 citations recorded by the source corpus.

In reinforcement learning (RL), function approximation errors are known to easily lead to the <inline-formula> <tex-math notation="LaTeX">$Q$ </tex-math></inline-formula>-value overestimations, thus greatly reducing policy performance. This article presents a distributional soft actor–critic (DSAC) algorithm, which is an off-policy RL method for continuous control setting, to improve the policy performance by mitigating <inline-formula> <tex-math notation="LaTeX">$Q$ </tex-math></inline-formula>-value overestimations. We first discover in theory that learning a distribution function of state–action returns can effectively mitigate <inline-formula> <tex-math notation="LaTeX">$Q$ </tex-math></inline-formula>-value overestimations because it is capable of adaptively adjusting the update step size of the <inline-formula> <tex-math notation="LaTeX">$Q$ </tex-math></inline-formula>-value function. Then, a distributional soft policy iteration (DSPI) framework is developed by embedding the return distribution function into maximum entropy RL. Finally, we present a deep off-policy actor–critic variant of DSPI, called DSAC, which directly learns a continuous return distribution by keeping the variance of the state–action returns within a reasonable range to address exploding and vanishing gradient problems. We evaluate DSAC on the suite of MuJoCo continuous control tasks, achieving the state-of-the-art performance.

Subfields: Artificial Intelligence, Computational Theory and Mathematics

View Paper: https://www.semanticscholar.org/paper/23a061f719c6c6f1f8c0b5157b5c5145ca2ef8b7