Shields to Guarantee Probabilistic Safety in MDPs

• URL: http://arxiv.org/abs/2605.10888v2
• Date: Wed, 13 May 2026 15:09:48 GMT
• Title: Shields to Guarantee Probabilistic Safety in MDPs
• Abstract summary: This paper presents a formal framework that conservatively extends classical shields to probabilistic safety.<n>In this framework, we (i) demonstrate the impossibility of preserving the strong guarantees on safety and permissiveness, (ii) provide natural shields with weaker guarantees, and (iii) introduce offline and online shield constructions ensuring strong safety guarantees.
• Score: 3.788847276402066
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Shielding is a prominent model-based technique to ensure safety of autonomous agents. Classical shielding aims to ensure that nothing bad ever happens and comes with strong guarantees about safety and maximal permissiveness. However, shielding systems for probabilistic safety, where something bad is allowed to happen with an acceptable probability, has proven to be more intricate. This paper presents a formal framework that conservatively extends classical shields to probabilistic safety. In this framework, we (i) demonstrate the impossibility of preserving the strong guarantees on safety and permissiveness, (ii) provide natural shields with weaker guarantees, and (iii) introduce offline and online shield constructions ensuring strong safety guarantees. The empirical evaluation highlights the practical advantages of the new shields, as well as their computational feasibility.

Related papers

• Robust Shielding for Safe Reinforcement Learning [55.99069346593732]
  Shielding is an effective approach to formally guarantee the safety of reinforcement learning agents in Markov decision processes (MDPs)<n>We introduce a novel shielding framework for robust MDPs with sets of transition probabilities.<n>Our experiments show that our shields for learned MDPs guarantee safety in unknown MDPs while recovering strong expected return as the number of samples increases.
  arXiv  Detail & Related papers  (2026-05-29T19:01:12Z)
• Robust Probabilistic Shielding for Safe Offline Reinforcement Learning [12.352902259774345]
  In offline reinforcement learning, we learn policies from fixed datasets without environment interaction.<n>A technique called safe policy improvement (SPI) provides a performance guarantee: with high probability, the new policy outperforms a given baseline policy, which is assumed to be safe.<n>We integrate these paradigms by extending shielding to offline RL, relying solely on the available dataset and knowledge of safe and unsafe states.
  arXiv  Detail & Related papers  (2026-05-11T09:54:30Z)
• Predictive Safety Shield for Dyna-Q Reinforcement Learning [0.0]
  We propose a predictive safety shield for model-based reinforcement learning agents in discrete space.<n>Our safety shield updates the Q-function locally based on safe predictions, which originate from a safe simulation of the environment model.<n>Our experiments on gridworld environments demonstrate that even short prediction horizons can be sufficient to identify the optimal path.
  arXiv  Detail & Related papers  (2025-11-26T15:59:55Z)
• SafeR-CLIP: Mitigating NSFW Content in Vision-Language Models While Preserving Pre-Trained Knowledge [51.634837361795434]
  SaFeR-CLIP reconciles safety and performance, recovering up to 8.0% in zero-shot accuracy over prior methods.<n>We also contribute NSFW-Caps, a new benchmark of 1,000 highly-aligned pairs for testing safety under distributional shift.
  arXiv  Detail & Related papers  (2025-11-20T19:00:15Z)
• ProSh: Probabilistic Shielding for Model-free Reinforcement Learning [11.125968799758434]
  We introduce Probabilistic Shielding via Risk Augmentation (ProSh), a model-free algorithm for safe reinforcement learning under cost constraints.<n>ProSh enforces safety by applying a shield to the agent's policy distribution using a learned cost critic.<n>We show that optimality is preserved when the environment is deterministic.
  arXiv  Detail & Related papers  (2025-10-17T15:08:51Z)
• Towards provable probabilistic safety for scalable embodied AI systems [79.31011047593492]
  Embodied AI systems are increasingly prevalent across various applications.<n> Ensuring their safety in complex operating environments remains a major challenge.<n>This Perspective offers a pathway toward safer, large-scale adoption of embodied AI systems in safety-critical applications.
  arXiv  Detail & Related papers  (2025-06-05T15:46:25Z)
• Probabilistic Shielding for Safe Reinforcement Learning [51.35559820893218]
  In real-life scenarios, a Reinforcement Learning (RL) agent must often also behave in a safe manner, including at training time.<n>We present a new, scalable method, which enjoys strict formal guarantees for Safe RL.<n>We show that our approach provides a strict formal safety guarantee that the agent stays safe at training and test time.
  arXiv  Detail & Related papers  (2025-03-09T17:54:33Z)
• Realizable Continuous-Space Shields for Safe Reinforcement Learning [13.728961635717134]
  We present the first shielding approach specifically designed to ensure the satisfaction of safety requirements in continuous state and action spaces.<n>Our method builds upon realizability, an essential property that confirms the shield will always be able to generate a safe action for any state in the environment.
  arXiv  Detail & Related papers  (2024-10-02T21:08:11Z)
• Safety through Permissibility: Shield Construction for Fast and Safe Reinforcement Learning [57.84059344739159]
  "Shielding" is a popular technique to enforce safety inReinforcement Learning (RL) We propose a new permissibility-based framework to deal with safety and shield construction.
  arXiv  Detail & Related papers  (2024-05-29T18:00:21Z)
• Leveraging Approximate Model-based Shielding for Probabilistic Safety Guarantees in Continuous Environments [63.053364805943026]
  We extend the approximate model-based shielding framework to the continuous setting. In particular we use Safety Gym as our test-bed, allowing for a more direct comparison of AMBS with popular constrained RL algorithms.
  arXiv  Detail & Related papers  (2024-02-01T17:55:08Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.