Provable General Function Class Representation Learning In Multitask Bandits And Mdps

Abstract

While multitask representation learning has become a popular approach in reinforcement learning (RL) to boost the sample efficiency, the theoretical understanding of why and how it works is still limited. Most previous analytical works could only assume that the representation function is already known to the agent or from linear function class, since analyzing general function class representation encounters non-trivial technical obstacles such as generalization guarantee, formulation of confidence bound in abstract function space, etc. However, linear-case analysis heavily relies on the particularity of linear function class, while real-world practice usually adopts general non-linear representation functions like neural networks. This significantly reduces its applicability. In this work, we extend the analysis to general function class representations. Specifically, we consider an agent playing \(M\) contextual bandits (or MDPs) concurrently and extracting a shared representation f

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keylu2022provable

Related papers

• Towards Understanding The Benefit Of Multitask Representation Learning In Decision Process (2025)0.00
• Provable Benefit Of Multitask Representation Learning In Reinforcement Learning (2022)0.00
• Provable Multi-task Reinforcement Learning: A Representation Learning Framework With Low Rank Rewards (2026)0.00
• Provably Efficient Multi-task Reinforcement Learning With Model Transfer (2021)0.00
• Provable Benefits Of Multi-task RL Under Non-markovian Decision Making Processes (2023)0.00
• Towards A Pretrained Model For Restless Bandits Via Multi-arm Generalization (2023)0.00
• Scalable Spectral Representations For Multi-agent Reinforcement Learning In Network Mdps (2024)0.00
• On The Generalization Of Representations In Reinforcement Learning (2022)0.00