Safe Reinforcement Learning via Recovery-based Shielding with Gaussian Process Dynamics Models
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866918342080593920 |
|---|---|
| author | Goodall, Alexander W. Belardinelli, Francesco |
| author_facet | Goodall, Alexander W. Belardinelli, Francesco |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_12444 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Safe Reinforcement Learning via Recovery-based Shielding with Gaussian Process Dynamics Models Goodall, Alexander W. Belardinelli, Francesco Machine Learning Artificial Intelligence 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. |
| title | Safe Reinforcement Learning via Recovery-based Shielding with Gaussian Process Dynamics Models |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2602.12444 |