State-Action Joint Regularized Implicit Policy for Offline Reinforcement Learning

29 Sep 2021  ·  Shentao Yang, Zhendong Wang, Huangjie Zheng, Mingyuan Zhou ·

Offline reinforcement learning enables learning from a fixed dataset, without further interactions with the environment. The lack of environmental interactions makes the policy training vulnerable to state-action pairs far from the training dataset and prone to missing rewarding actions. For training more effective agents, we propose a framework that supports learning a flexible and well-regularized policy, which consists of a fully implicit policy and a regularization through the state-action visitation frequency induced by the current policy and that induced by the data-collecting behavior policy. We theoretically show the equivalence between policy-matching and state-action-visitation matching, and thus the compatibility of many prior work with our framework. An effective instantiation of our framework through the GAN structure is provided, together with some techniques to explicitly smooth the state-action mapping for robust generalization beyond the static dataset. Extensive experiments and ablation study on the D4RL dataset validate our framework and the effectiveness of our algorithmic designs.

PDF Abstract
No code implementations yet. Submit your code now

Datasets


Results from the Paper


  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.

Methods


No methods listed for this paper. Add relevant methods here