Provable Benefit Of Multitask Representation Learning In Reinforcement Learning

Abstract

As representation learning becomes a powerful technique to reduce sample complexity in reinforcement learning (RL) in practice, theoretical understanding of its advantage is still limited. In this paper, we theoretically characterize the benefit of representation learning under the low-rank Markov decision process (MDP) model. We first study multitask low-rank RL (as upstream training), where all tasks share a common representation, and propose a new multitask reward-free algorithm called REFUEL. REFUEL learns both the transition kernel and the near-optimal policy for each task, and outputs a well-learned representation for downstream tasks. Our result demonstrates that multitask representation learning is provably more sample-efficient than learning each task individually, as long as the total number of tasks is above a certain threshold. We then study the downstream RL in both online and offline settings, where the agent is assigned with a new task sharing the same representation as

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keycheng2022provable

Related papers

• Towards Understanding The Benefit Of Multitask Representation Learning In Decision Process (2025)0.00
• 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
• Provable General Function Class Representation Learning In Multitask Bandits And Mdps (2022)0.00
• Accelerating Multi-task Temporal Difference Learning Under Low-rank Representation (2025)0.00
• Provably Efficient Multi-task Reinforcement Learning With Model Transfer (2021)0.00
• Improved Sample Complexity For Reward-free Reinforcement Learning Under Low-rank Mdps (2023)0.00
• A Model-based Approach For Sample-efficient Multi-task Reinforcement Learning (2019)0.00