Yu-Xiang Wang (UC Santa Barbara)
The problem of Offline Policy Evaluation (OPE) in Reinforcement Learning (RL) is a critical step towards applying RL in real-life applications. Existing work on OPE mostly focus on evaluating a fixed target policy π, which does not provide useful bounds for offline policy learning as π will then be data-dependent. We address this problem by simultaneously evaluating all policies in a policy class Π -- uniform convergence in OPE -- and obtain nearly optimal error bounds for a number of global / local policy classes. Our results imply that the model-based planning achieves an optimal episode complexity of O˜(H3/dmϵ2) in identifying an ϵ-optimal policy under the time-inhomogeneous episodic MDP model (H is the planning horizon, dm is a quantity that reflects the exploration of the logging policy μ). To the best of our knowledge, this is the first time the optimal rate is shown to be possible for the offline RL setting and the paper is the first that systematically investigates the uniform convergence in OPE.