mlsanityData to 14 Oct 2026

Shields to Guarantee Probabilistic Safety in MDPs

arXiv 2605.10888 ↗First posted 11 May 2026cs.LO cs.AIcited by 2

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 28 of its 47 references that are in the map. First posted on arXiv 11 May 2026.

Builds on

28 of 47 references.

References · 28

  1. 2017Safe Reinforcement Learning via Shieldingcited by 449
  2. 2023The Safety Filter: A Unified View of Safety-Critical Control in Autonomous Systemscited by 88
  3. 2020The Probabilistic Model Checker Stormcited by 66
  4. 2021Safe Multi-Agent Reinforcement Learning via Shieldingcited by 61
  5. 2022Safe Reinforcement Learning via Shielding under Partial Observabilitycited by 56
  6. 2020Cautious Reinforcement Learning with Logical Constraintscited by 45
  7. 2023Safe Reinforcement Learning via Probabilistic Logic Shieldscited by 42
  8. 2022Provably Safe Reinforcement Learning: Conceptual Analysis, Survey, and Benchmarkingcited by 34
  9. 2015Safety-Constrained Reinforcement Learning for MDPscited by 33
  10. 2019Neural Simplex Architecturecited by 29
  11. 2022Provably Safe Reinforcement Learning via Action Projection using Reachability Analysis and Polynomial Zonotopescited by 26
  12. 2022Online Shielding for Reinforcement Learningcited by 22
16 more
  1. 2020Adaptive Shielding under Uncertaintycited by 18
  2. 2015Permissive Controller Synthesis for Probabilistic Systemscited by 17
  3. 2024Shield Synthesis for LTL Modulo Theoriescited by 12
  4. 2025Probabilistic Shielding for Safe Reinforcement Learningcited by 12
  5. 2022Dynamic Shielding for Reinforcement Learning in Black-Box Environmentscited by 11
  6. 2022Automata Learning meets Shieldingcited by 9
  7. 2023Safe POMDP Online Planning via Shieldingcited by 8
  8. 2024Compositional Shielding and Reinforcement Learning for Multi-Agent Systemscited by 8
  9. 2016Optimizing Expectation with Guarantees in POMDPs (Technical Report)cited by 7
  10. 2024Safe Reinforcement Learning in Black-Box Environments via Adaptive Shieldingcited by 6
  11. 2020Reinforcement Learning of Risk-Constrained Policies in Markov Decision Processescited by 5
  12. 2025Adaptive Shielding via Parametric Safety Proofscited by 5
  13. 2021On Optimizing the Conditional Value-at-Risk of a Maximum Cost for Risk-Averse Safety Analysiscited by 4
  14. 2025The Use of the Simplex Architecture to Enhance Safety in Deep-Learning-Powered Autonomous Systemscited by 2
  15. 2023Formally-Sharp DAgger for MCTS: Lower-Latency Monte Carlo Tree Search using Data Aggregation with Formal Methodscited by 1
  16. 2026Finite-State Controllers for (Hidden-Model) POMDPs using Deep Reinforcement Learningcited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026Cycle-Consistent Neural Explanation of Formal Verification Certificatescited by 0
  2. 2026Adaptive Probabilistic Shielding by Learning MDPs for Safe Reinforcement Learningcited by 0