Marcel Vinzent

2 accepted papers

2026

Probabilistic Safety Verification of Neural Policies via Predicate Abstraction

Marcel Vinzent, Holger Hermanns, Jörg Hoffmann

AAAI 2026technical

Neural networks are increasingly important to learn action policies. Policy predicate abstraction (PPA) verifies safety of such a neural policy pi by over-approximating the state space subgraph induced by pi and using counterexample-guided abstraction refinement (CEGAR) to iteratively refine the abs

Cited by 0 Source ↗PDF ↗Scholar ↗

2023

Neural Policy Safety Verification via Predicate Abstraction: CEGAR

Marcel Vinzent, Siddhant Sharma, Jöerg Hoffmann

AAAI 2023technical

Neural networks (NN) are an increasingly important representation of action policies pi. Recent work has extended predicate abstraction to prove safety of such pi, through policy predicate abstraction (PPA) which over-approximates the state space subgraph induced by pi. The advantage of PPA is that…

Cited by 9 Source ↗PDF ↗Scholar ↗