Timezone: »

 
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 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