Provably Efficient Multi-task Reinforcement Learning With Model Transfer

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.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyzhang2021provably

Related papers

• Provable Multi-task Reinforcement Learning: A Representation Learning Framework With Low Rank Rewards (2026)0.00
• Provable Benefits Of Multi-task RL Under Non-markovian Decision Making Processes (2023)0.00
• Reinforcement Learning In The Wild With Maximum Likelihood-based Model Transfer (2023)0.00
• Model-based Reinforcement Learning With Multinomial Logistic Function Approximation (2022)2.26
• A Decentralized Policy Gradient Approach To Multi-task Reinforcement Learning (2020)0.00
• Lipschitz Lifelong Reinforcement Learning (2020)8.35
• Provable Benefit Of Multitask Representation Learning In Reinforcement Learning (2022)0.00
• Scaling Distributed Multi-task Reinforcement Learning With Experience Sharing (2023)0.00