Pessimistic Model Selection for Offline Deep Reinforcement Learning

Abstract

Deep Reinforcement Learning (DRL) has demonstrated great potentials in solving sequential decision making problems in many applications. Despite its promising performance, practical gaps exist when deploying DRL in real-world scenarios. One main barrier is the over-fitting issue that leads to poor generalizability of the policy learned by DRL. In particular, for offline DRL with observational data, model selection is a challenging task as there is no ground truth available for performance demonstration, in contrast with the online setting with simulated environments. In this work, we propose a pessimistic model selection (PMS) approach for offline DRL with a theoretical guarantee, which features a provably effective framework for finding the best policy among a set of candidate models. Two refined approaches are also proposed to address the potential bias of DRL model in identifying the optimal policy. Numerical studies demonstrated the superior performance of our approach over existing methods.

Preprint. A non-archival and preliminary venue was presented at NeurIPS 2021 Offline Reinforcement Learning Workshop

References in corpus (11)

• Conservative Q-Learning for Offline Reinforcement Learning
• Behavior Regularized Offline Reinforcement Learning
• Distributional Reinforcement Learning with Quantile Regression
• Model Selection for Offline Reinforcement Learning: Practical Considerations for Healthcare Settings
• A Survey of Deep Reinforcement Learning in Recommender Systems: A Systematic Review and Future Directions
• Bellman-consistent Pessimism for Offline Reinforcement Learning
• Provable Benefits of Actor-Critic Methods for Offline Reinforcement Learning
• Finite Sample Analysis of Minimax Offline Reinforcement Learning: Completeness, Fast Rates and First-Order Efficiency
• Doubly Robust Bias Reduction in Infinite Horizon Off-Policy Estimation
• Clinician-in-the-Loop Decision Making: Reinforcement Learning with Near-Optimal Set-Valued Policies
• Offline Policy Selection under Uncertainty