Salvato in:
Dettagli Bibliografici
Autori principali: Roch, Zachary, Zhang, Chi, Atia, George, Wang, Yue
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2505.12462
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866911174974504960
author Roch, Zachary
Zhang, Chi
Atia, George
Wang, Yue
author_facet Roch, Zachary
Zhang, Chi
Atia, George
Wang, Yue
contents Robust reinforcement learning (RL) under the average-reward criterion is essential for long-term decision-making, particularly when the environment may differ from its specification. However, a significant gap exists in understanding the finite-sample complexity of these methods, as most existing work provides only asymptotic guarantees. This limitation hinders their principled understanding and practical deployment, especially in data-limited scenarios. We close this gap by proposing \textbf{Robust Halpern Iteration (RHI)}, a new algorithm designed for robust Markov Decision Processes (MDPs) with transition uncertainty characterized by $\ell_p$-norm and contamination models. Our approach offers three key advantages over previous methods: (1). Weaker Structural Assumptions: RHI only requires the underlying robust MDP to be communicating, a less restrictive condition than the commonly assumed ergodicity or irreducibility; (2). No Prior Knowledge: Our algorithm operates without requiring any prior knowledge of the robust MDP; (3). State-of-the-Art Sample Complexity: To learn an $ε$-optimal robust policy, RHI achieves a sample complexity of $\tilde{\mathcal O}\left(\frac{SA\mathcal H^{2}}{ε^{2}}\right)$, where $S$ and $A$ denote the numbers of states and actions, and $\mathcal H$ is the robust optimal bias span. This result represents the tightest known bound. Our work hence provides essential theoretical understanding of sample efficiency of robust average reward RL.
format Preprint
id arxiv_https___arxiv_org_abs_2505_12462
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Provably Sample-Efficient Robust Reinforcement Learning with Average Reward
Roch, Zachary
Zhang, Chi
Atia, George
Wang, Yue
Machine Learning
Robust reinforcement learning (RL) under the average-reward criterion is essential for long-term decision-making, particularly when the environment may differ from its specification. However, a significant gap exists in understanding the finite-sample complexity of these methods, as most existing work provides only asymptotic guarantees. This limitation hinders their principled understanding and practical deployment, especially in data-limited scenarios. We close this gap by proposing \textbf{Robust Halpern Iteration (RHI)}, a new algorithm designed for robust Markov Decision Processes (MDPs) with transition uncertainty characterized by $\ell_p$-norm and contamination models. Our approach offers three key advantages over previous methods: (1). Weaker Structural Assumptions: RHI only requires the underlying robust MDP to be communicating, a less restrictive condition than the commonly assumed ergodicity or irreducibility; (2). No Prior Knowledge: Our algorithm operates without requiring any prior knowledge of the robust MDP; (3). State-of-the-Art Sample Complexity: To learn an $ε$-optimal robust policy, RHI achieves a sample complexity of $\tilde{\mathcal O}\left(\frac{SA\mathcal H^{2}}{ε^{2}}\right)$, where $S$ and $A$ denote the numbers of states and actions, and $\mathcal H$ is the robust optimal bias span. This result represents the tightest known bound. Our work hence provides essential theoretical understanding of sample efficiency of robust average reward RL.
title Provably Sample-Efficient Robust Reinforcement Learning with Average Reward
topic Machine Learning
url https://arxiv.org/abs/2505.12462