paper-with-me

Papers

Provable Representation with Efficient Planning for Partial Observable Reinforcement Learning

2023-11-20 · Hongming Zhang, Tongzheng Ren, Chenjun Xiao, Dale Schuurmans, Bo Dai

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.

📄 PDF Abstract BibTeX arXiv:2311.12244

Code (0)

등록된 구현이 없습니다.

Tasks

Partially Observable Reinforcement Learningreinforcement-learningReinforcement Learning

Similar Papers 제목 키워드 기반

Partially Observable Multi-Agent Reinforcement Learning with Information Sharing

2023-08-16 · Xiangyu Liu, Kaiqing Zhang

We study provable multi-agent reinforcement learning (RL) in the general framework of partially observable stochastic games (POSGs). To circumvent the known hardness results and the use of computationally intractable ora…

Computational EfficiencyMulti-agent Reinforcement Learningreinforcement-learningReinforcement Learning+1

Planning in Observable POMDPs in Quasipolynomial Time

2022-01-12 · Noah Golowich, Ankur Moitra, Dhruv Rohatgi

Partially Observable Markov Decision Processes (POMDPs) are a natural and general model in reinforcement learning that take into account the agent's uncertainty about its current state. In the literature on POMDPs, it is…

Provable Partially Observable Reinforcement Learning with Privileged Information

2024-12-01 · Yang Cai, Xiangyu Liu, Argyris Oikonomou, Kaiqing Zhang

Partial observability of the underlying states generally presents significant challenges for reinforcement learning (RL). In practice, certain \emph{privileged information}, e.g., the access to states from simulators, ha…

Partially Observable Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)

A Point-Based Algorithm for Distributional Reinforcement Learning in Partially Observable Domains

2025-05-10 · Larry Preuett III

In many real-world planning tasks, agents must tackle uncertainty about the environment's state and variability in the outcomes of any chosen policy. We address both forms of uncertainty as a first step toward safer algo…

Decision MakingDistributional Reinforcement Learning

Benchmarking Partial Observability in Reinforcement Learning with a Suite of Memory-Improvable Domains

2025-07-31 · Ruo Yu Tao, Kaicheng Guo, Cameron Allen, George Konidaris arxiv

Mitigating partial observability is a necessary but challenging task for general reinforcement learning algorithms. To improve an algorithm's ability to mitigate partial observability, researchers need comprehensive benc…

General Reinforcement Learning