arXiv cs.AI· Alexander W. Goodall, Francesco Belardinelli·· 12 小时前AI 评分29
RecReg：用基于恢复的屏蔽机制在强化学习中强制执行非马尔可夫正则安全属性
RECREG: Recovery-based Shielding for Regular Safety Properties in Reinforcement Learning
AI 导读
RecReg 是一个通过基于恢复的屏蔽（recovery-based shielding）来强制执行非马尔可夫正则安全属性的安全强化学习框架，支持不同级别的先验知识与安全保证。
正文 · 原文
Abstract:In many real-world scenarios we need to consider formal requirements, such as safety and constraint compliance, to deploy Reinforcement Learning (RL) agents. In this paper we introduce RecReg, a safe RL framework capable of enforcing non-Markovian regular safety properties via recovery-based shielding. RecReg is a unified approach that supports different levels of a priori knowledge and safety guarantees. The paper primarily focuses on building the theoretical foundations for RecReg in the tabular setting, providing rigorous safety and convergence guarantees that are not present in related work. We provide an extensive set of empirical results using the MASA-Safe-RL library, and we outline an extension of RecReg to deep RL domains using SOTA model-based RL. Our empirical results demonstrate that RecReg achieves efficient learning and matches the theory in this paper.
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.23445 [cs.LG] |
| (or arXiv:2610.23445v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.23445 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Alexander W. Goodall [view email]
[v1]
Fri, 16 Oct 2026 13:28:34 UTC (6,118 KB)
来源：arXiv cs.AI · arxiv.org