Advantage-Aware Policy Optimization for Offline Reinforcement Learning

Offline Reinforcement Learning (RL) endeavors to leverage offline datasets to craft effective agent policy without online interaction, which imposes proper conservative constraints with the support of behavior policies to tackle the Out-Of-Distribution (OOD) problem. However, existing works often suffer from the constraint conflict issue when offline datasets are collected from multiple behavior policies, i.e., different behavior policies may exhibit inconsistent actions with distinct returns across the state space. To remedy this issue, recent Advantage-Weighted (AW) methods prioritize samples with high advantage values for agent training while inevitably leading to overfitting on these samples. In this paper, we introduce a novel Advantage-Aware Policy Optimization (A2PO) method to explicitly construct advantage-aware policy constraints for offline learning under mixed-quality datasets. Specifically, A2PO employs a Conditional Variational Auto-Encoder (CVAE) to disentangle the action distributions of intertwined behavior policies by modeling the advantage values of all training data as conditional variables. Then the agent can follow such disentangled action distribution constraints to optimize the advantage-aware policy towards high advantage values. Extensive experiments conducted on both the single-quality and mixed-quality datasets of the D4RL benchmark demonstrate that A2PO yields results superior to state-of-the-art counterparts. Our code will be made publicly available.