Policy Finetuning in Reinforcement Learning via Design of Experiments using Offline Data

Part of Advances in Neural Information Processing Systems 36 (NeurIPS 2023) Main Conference Track

Authors

Ruiqi Zhang, Andrea Zanette

Abstract

In some applications of reinforcement learning, a dataset of pre-collected experience is already availablebut it is also possible to acquire some additional online data to help improve the quality of the policy.However, it may be preferable to gather additional data with a single, non-reactive exploration policyand avoid the engineering costs associated with switching policies. In this paper we propose an algorithm with provable guarantees that can leverage an offline dataset to design a single non-reactive policy for exploration. We theoretically analyze the algorithm and measure the quality of the final policy as a function of the local coverage of the original dataset and the amount of additional data collected.