Actor-critic (AC) methods are ubiquitous in reinforcement learning. Although it is understood that AC methods are closely related to policy gradient (PG), their precise connection has not been fully characterized previously. In this paper, we explain the gap between AC and PG methods by identifying the exact adjustment to the AC objective/gradient that recovers the true policy gradient of the cumulative reward objective (PG). Furthermore, by viewing the AC method as a two-player Stackelberg game between the actor and critic, we show that the Stackelberg policy gradient can be recovered as a special case of our more general analysis. Based on these results, we develop practical algorithms, Residual Actor-Critic and Stackelberg Actor-Critic, for estimating the correction between AC and PG and use these to modify the standard AC algorithm. Experiments on popular tabular and continuous environments show the proposed corrections can improve both the sample efficiency and final performance of existing AC methods.

本文提出了一种旨在改进强化学习中Actor-critic方法的算法——Residual Actor-Critic和Stackelberg Actor-Critic，可以提高现有方法的样本效率和最终性能，并通过对Actor和Critic之间的两人博弈进行深入分析, 建立了它们与政策梯度方法的确切联系。

演员-评论家和策略梯度之间的差距表征