SelfBC: Self Behavior Cloning for Offline Reinforcement Learning
This work addresses a key limitation in offline RL for improving policy performance without collapse, though it is incremental as it builds on existing policy constraint methods.
The paper tackles the problem of overly conservative policies in offline reinforcement learning by proposing a dynamic policy constraint that uses an exponential moving average of previously learned policies, achieving state-of-the-art performance on the D4RL MuJoCo domain.
Policy constraint methods in offline reinforcement learning employ additional regularization techniques to constrain the discrepancy between the learned policy and the offline dataset. However, these methods tend to result in overly conservative policies that resemble the behavior policy, thus limiting their performance. We investigate this limitation and attribute it to the static nature of traditional constraints. In this paper, we propose a novel dynamic policy constraint that restricts the learned policy on the samples generated by the exponential moving average of previously learned policies. By integrating this self-constraint mechanism into off-policy methods, our method facilitates the learning of non-conservative policies while avoiding policy collapse in the offline setting. Theoretical results show that our approach results in a nearly monotonically improved reference policy. Extensive experiments on the D4RL MuJoCo domain demonstrate that our proposed method achieves state-of-the-art performance among the policy constraint methods.