Timezone: »
Poster
Provably efficient multi-task reinforcement learning with model transfer
Chicheng Zhang · Zhi Wang
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.
Author Information
Chicheng Zhang (University of Arizona)
Zhi Wang (University of California San Diego)
More from the Same Authors
-
2022 Poster: PopArt: Efficient Sparse Regression and Experimental Design for Optimal Sparse Linear Bandits »
Kyoungseok Jang · Chicheng Zhang · Kwang-Sung Jun -
2022 Poster: On Efficient Online Imitation Learning via Classification »
Yichen Li · Chicheng Zhang -
2020 Poster: Crush Optimism with Pessimism: Structured Bandits Beyond Asymptotic Optimality »
Kwang-Sung Jun · Chicheng Zhang -
2020 Poster: Efficient active learning of sparse halfspaces with arbitrary bounded noise »
Chicheng Zhang · Jie Shen · Pranjal Awasthi -
2020 Poster: Efficient Contextual Bandits with Continuous Actions »
Maryam Majzoubi · Chicheng Zhang · Rajan Chari · Akshay Krishnamurthy · John Langford · Aleksandrs Slivkins -
2020 Oral: Efficient active learning of sparse halfspaces with arbitrary bounded noise »
Chicheng Zhang · Jie Shen · Pranjal Awasthi