Provably efficient multi-task reinforcement learning with model transfer

Part of Advances in Neural Information Processing Systems 34 (NeurIPS 2021)

Authors

Chicheng Zhang, Zhi Wang

Abstract

We study multi-task reinforcement learning (RL) in tabular episodic Markov decision processes (MDPs). We formulate a heterogeneous multi-player RL problem, in which a group of players concurrently face similar but not necessarily identical MDPs, with a goal of improving their collective performance through inter-player information sharing. We design and analyze a model-based algorithm, and provide gap-dependent and gap-independent regret upper and lower bounds that characterize the intrinsic complexity of the problem.