Shields to Guarantee Probabilistic Safety in MDPs

ArXi:2605.10888v1 Announce Type: cross 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 intricate. This paper presents a formal framework that conservatively extends classical shields to probabilistic safety.