arXiv cs.AI· Alexander W. Goodall, Francesco Belardinelli·· 11 小时前AI 评分24
基于高斯过程动力学模型与恢复式屏蔽的安全强化学习
Safe Reinforcement Learning via Recovery-based Shielding with Gaussian Process Dynamics Models
AI 导读
研究者提出一种恢复式屏蔽框架，为未知非线性连续动力系统提供可证明的安全下界。该方法将备份策略（shield）与 RL 智能体结合，用高斯过程量化不确定性以预测安全约束违反，仅在必要时恢复至安全轨迹。屏蔽智能体的经验用于构建 GP 模型，并通过内部基于模型的采样优化策略，在连续控制环境中实现严格安全合规与样本高效学习。
正文 · 原文
Abstract:Reinforcement learning (RL) is a powerful framework for optimal decision-making and control but often lacks provable guarantees for safety-critical applications. In this paper, we introduce a novel recovery-based shielding framework that enables safe RL with a provable safety lower bound for unknown and non-linear continuous dynamical systems. The proposed approach integrates a backup policy (shield) with the RL agent, leveraging Gaussian process (GP) based uncertainty quantification to predict potential violations of safety constraints, dynamically recovering to safe trajectories only when necessary. Experience gathered by the 'shielded' agent is used to construct the GP models, with policy optimization via internal model-based sampling - enabling unrestricted exploration and sample efficient learning, without compromising safety. Empirically our approach demonstrates strong performance and strict safety-compliance on a suite of continuous control environments.
| Comments: | AAMAS 2026 |
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2602.12444 [cs.LG] |
| (or arXiv:2602.12444v3 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2602.12444 arXiv-issued DOI via DataCite |
|
| Related DOI: | https://doi.org/10.65109/EAHU8566
DOI(s) linking to related resources |
Submission history
From: Alexander W. Goodall [view email]
[v1]
Thu, 12 Feb 2026 22:03:35 UTC (548 KB)
[v2]
Tue, 17 Feb 2026 09:48:52 UTC (543 KB)
[v3]
Fri, 30 Oct 2026 10:42:27 UTC (543 KB)
来源：arXiv cs.AI · arxiv.org