Offline Reinforcement Learning with OOD State Correction and OOD Action Suppression

TL;DR

This paper introduces SCAS, a method for offline RL that addresses both OOD states and actions, improving performance and robustness without extra hyperparameter tuning.

Contribution

SCAS unifies OOD state correction and action suppression in offline RL, effectively improving performance and robustness.

Findings

SCAS outperforms existing methods on standard benchmarks.

SCAS effectively suppresses OOD actions.

SCAS enhances robustness against environmental perturbations.

Abstract

In offline reinforcement learning (RL), addressing the out-of-distribution (OOD) action issue has been a focus, but we argue that there exists an OOD state issue that also impairs performance yet has been underexplored. Such an issue describes the scenario when the agent encounters states out of the offline dataset during the test phase, leading to uncontrolled behavior and performance degradation. To this end, we propose SCAS, a simple yet effective approach that unifies OOD state correction and OOD action suppression in offline RL. Technically, SCAS achieves value-aware OOD state correction, capable of correcting the agent from OOD states to high-value in-distribution states. Theoretical and empirical results show that SCAS also exhibits the effect of suppressing OOD actions. On standard offline RL benchmarks, SCAS achieves excellent performance without additional hyperparameter tuning. Moreover, benefiting from its OOD state correction feature, SCAS demonstrates enhanced robustness against environmental perturbations.