English

Provable Representation with Efficient Planning for Partial Observable Reinforcement Learning

Machine Learning 2024-06-12 v3 Artificial Intelligence Machine Learning

Abstract

In most real-world reinforcement learning applications, state information is only partially observable, which breaks the Markov decision process assumption and leads to inferior performance for algorithms that conflate observations with state. Partially Observable Markov Decision Processes (POMDPs), on the other hand, provide a general framework that allows for partial observability to be accounted for in learning, exploration and planning, but presents significant computational and statistical challenges. To address these difficulties, we develop a representation-based perspective that leads to a coherent framework and tractable algorithmic approach for practical reinforcement learning from partial observations. We provide a theoretical analysis for justifying the statistical efficiency of the proposed algorithm, and also empirically demonstrate the proposed algorithm can surpass state-of-the-art performance with partial observations across various benchmarks, advancing reliable reinforcement learning towards more practical applications.

Keywords

Cite

@article{arxiv.2311.12244,
  title  = {Provable Representation with Efficient Planning for Partial Observable Reinforcement Learning},
  author = {Hongming Zhang and Tongzheng Ren and Chenjun Xiao and Dale Schuurmans and Bo Dai},
  journal= {arXiv preprint arXiv:2311.12244},
  year   = {2024}
}

Comments

The first two authors contribute equally

R2 v1 2026-06-28T13:26:49.034Z