Pseudometric guided online query and update for offline reinforcement learning

Offline Reinforcement Learning (RL) extracts effective policies from historical data without the need to interact with the environment. However, the learned policy often suffers large generalization errors in the online environment due to the distributional shift. While existing work mostly focuses on learning a generalizable policy, we propose to adapt the learned policy to fit the online environment with limited queries. The goals include querying reasonable actions with limited chances and efficiently modifying the policy. Our insight is to unify these two goals via a proper pseudometric. Intuitively, the metric can compare online and offline states to infer optimal query actions. Additionally, efficient policy updates require good knowledge of the similarity between query results and historical data. Therefore, we propose a unified framework, denoted Pseudometric Guided Offline-to-Online RL (PGO2). Specifically, in deep Q learning, PGO2 has a structural design between the Q-neural network and the Siamese network, which guarantees simultaneous Q-network updating and pseudometric learning, promoting Q-network fine-tuning. In the inference phase, PGO2 solves convex optimizations to identify optimal query actions. We also show that PGO2 training converges to the so-called bisimulation metric with strong theoretical guarantees. Finally, we demonstrate the superiority of PGO2 on diversified datasets.