paper-with-me

Papers

Efficient Reinforcement Learning with Impaired Observability: Learning to Act with Delayed and Missing State Observations

2023-06-02 · Minshuo Chen, Jie Meng, Yu Bai, Yinyu Ye, H. Vincent Poor, Mengdi Wang

In real-world reinforcement learning (RL) systems, various forms of {\it impaired observability} can complicate matters. These situations arise when an agent is unable to observe the most recent state of the system due to latency or lossy channels, yet the agent must still make real-time decisions. This paper introduces a theoretical investigation into efficient RL in control systems where agents must act with delayed and missing state observations. We present algorithms and establish near-optimal regret upper and lower bounds, of the form $\tilde{\mathcal{O}}(\sqrt{{\rm poly}(H) SAK})$, for RL in the delayed and missing observation settings. Here $S$ and $A$ are the sizes of state and action spaces, $H$ is the time horizon and $K$ is the number of episodes. Despite impaired observability posing significant challenges to the policy class and planning, our results demonstrate that learning remains efficient, with the regret bound optimally depending on the state-action size of the original system. Additionally, we provide a characterization of the performance of the optimal policy under impaired observability, comparing it to the optimal value obtained with full observability. Numerical results are provided to support our theory.

📄 PDF Abstract BibTeX arXiv:2306.01243

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning (RL)

Similar Papers 제목 키워드 기반

Efficient RL with Impaired Observability: Learning to Act with Delayed and Missing State Observations

2023-09-21 · NeurIPS 2023 11

In real-world reinforcement learning (RL) systems, various forms of {\it impaired observability} can complicate matters. These situations arise when an agent is unable to observe the most recent state of the system due t…

Reinforcement Learning from Delayed Observations via World Models

2024-03-18 · Armin Karamzade, KyungMin Kim, Montek Kalsi, Roy Fox

In standard reinforcement learning settings, agents typically assume immediate feedback about the effects of their actions after taking them. However, in practice, this assumption may not hold true due to physical constr…

continuous-controlContinuous Controlreinforcement-learningReinforcement Learning

A Framework of decision-relevant observability: Reinforcement Learning converges under relative ignorability

2025-04-10 · MaryLena Bleile

From clinical dosing algorithms to autonomous robots, sequential decision-making systems routinely operate with missing or incomplete data. Classical reinforcement learning theory, which is commonly used to solve sequent…

Causal InferenceDecision MakingLearning TheoryQ-Learning+3

DATD3: Depthwise Attention Twin Delayed Deep Deterministic Policy Gradient For Model Free Reinforcement Learning Under Output Feedback Control

2025-05-29 · Wuhao Wang, Zhiyong Chen

Reinforcement learning in real-world applications often involves output-feedback settings, where the agent receives only partial state information. To address this challenge, we propose the Output-Feedback Markov Decisio…

continuous-controlContinuous ControlDecision Making

Communication Gain and Delay Cost Under Cross-Timestep Delays in Cooperative Multi-Agent Reinforcement Learning

2026-04-04 · Zihong Gao, Hongjian Liang, Lei Hao, Liangjun Ke arxiv

Communication is essential for coordination in \emph{cooperative} multi-agent reinforcement learning under partial observability, yet \emph{cross-timestep} delays cause messages to arrive multiple timesteps after generat…

Multi-agent Reinforcement Learning