Shields to Guarantee Probabilistic Safety in MDPs
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_ | 1866917490323357696 |
|---|---|
| author | Heck, Linus Macák, Filip Andriushchenko, Roman Češka, Milan Junges, Sebastian |
| author_facet | Heck, Linus Macák, Filip Andriushchenko, Roman Češka, Milan Junges, Sebastian |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_10888 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Shields to Guarantee Probabilistic Safety in MDPs Heck, Linus Macák, Filip Andriushchenko, Roman Češka, Milan Junges, Sebastian Logic in Computer Science Artificial Intelligence 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. |
| title | Shields to Guarantee Probabilistic Safety in MDPs |
| topic | Logic in Computer Science Artificial Intelligence |
| url | https://arxiv.org/abs/2605.10888 |