Robust Shielding for Safe Reinforcement Learning

2026-05-29 · Edwin Hamel-De le Court, Thom Badings, Alessandro Abate, Francesco Belardinelli, Francesco Fabiano arxiv

Shielding is an effective approach to formally guarantee the safety of reinforcement learning agents in Markov decision processes (MDPs). However, existing shielding techniques typically assume knowledge of the safety-relevant transition dynamics - a requirement that is seldom met in practice. To address this limitation, we introduce a novel shielding framework for robust MDPs (RMDPs), i.e., MDPs with sets of transition probabilities. We define safety as the satisfaction of a linear temporal logic (LTL) formula with a certain threshold probability under the worst-case transition probabilities of the RMDP. We prove that our shielding framework is both sound and optimal for the RMDP: every policy admissible by the shield is safe, and conversely, every safe RMDP policy is admissible by the shield. We combine our approach with existing sampling methods for learning transition probabilities of MDPs with probably approximately correct (PAC) guarantees. This combination enables the construction of shields for MDPs that, with high confidence, guarantee safety while remaining minimally restrictive. Our experiments show that our shields for learned RMDPs guarantee safety in unknown MDPs while recovering strong expected return as the number of samples increases.

📄 PDF Abstract BibTeX arXiv:2606.00270

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning

Safe Multi-Agent Reinforcement Learning via Shielding

2021-01-27 · Ingy Elsayed-Aly, Suda Bharadwaj, Christopher Amato, Rüdiger Ehlers 외

Multi-agent reinforcement learning (MARL) has been increasingly used in a wide range of safety-critical applications, which require guaranteed safety (e.g., no unsafe states are ever visited) during the learning process.…

Multi-agent Reinforcement Learning reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Approximate Model-Based Shielding for Safe Reinforcement Learning

2023-07-27 · Alexander W. Goodall, Francesco Belardinelli

Reinforcement learning (RL) has shown great potential for solving complex tasks in a variety of domains. However, applying RL to safety-critical systems in the real-world is not easy as many algorithms are sample-ineffic…

Atari Games model reinforcement-learning Reinforcement Learning+2

Do Androids Dream of Electric Fences? Safety-Aware Reinforcement Learning with Latent Shielding

2021-12-21 · Peter He, Borja G. Leon, Francesco Belardinelli

The growing trend of fledgling reinforcement learning systems making their way into real-world applications has been accompanied by growing concerns for their safety and robustness. In recent years, a variety of approach…

Deep Reinforcement Learning reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Safe Reinforcement Learning via Probabilistic Logic Shields

2023-03-06 · Wen-Chi Yang, Giuseppe Marra, Gavin Rens, Luc De Raedt

Safe Reinforcement learning (Safe RL) aims at learning optimal policies while staying safe. A popular solution to Safe RL is shielding, which uses a logical safety specification to prevent an RL agent from taking unsafe …

reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)Safe Reinforcement Learning

Easy-to-Use Shielding for Reinforcement Learning

2026-06-02 · Stefan Pranger, Bettina Könighofer arxiv

Safe exploration is a key challenge in Reinforcement Learning (RL) that aims to prevent agents from making harmful decisions while exploring their environment. Safe exploration is a key challenge in Reinforcement Learnin…