Provably Efficient Multi-Task Reinforcement Learning with Model Transfer

Chicheng Zhang; Zhi Wang

Provably Efficient Multi-Task Reinforcement Learning with Model Transfer

Machine Learning 2022-01-19 v2

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 an algorithm based on the idea of model transfer, and provide gap-dependent and gap-independent upper and lower bounds that characterize the intrinsic complexity of the problem.

Keywords

reinforcement learning multi-task learning multi-agent reinforcement learning

Cite

@article{arxiv.2107.08622,
  title  = {Provably Efficient Multi-Task Reinforcement Learning with Model Transfer},
  author = {Chicheng Zhang and Zhi Wang},
  journal= {arXiv preprint arXiv:2107.08622},
  year   = {2022}
}

Related papers

View all related →

Artificial Intelligence · Computer Science

Transfer from Multiple MDPs

Alessandro Lazaric, Marcello Restelli

2011-09-02

Machine Learning · Statistics

Model-Based Reinforcement Learning with Multinomial Logistic Function Approximation