LTL Verification of Memoryful Neural Agents

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Hosseini, Mehran, Lomuscio, Alessio, Paoletti, Nicola
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866917944968085504
author Hosseini, Mehran
Lomuscio, Alessio
Paoletti, Nicola
author_facet Hosseini, Mehran
Lomuscio, Alessio
Paoletti, Nicola
contents We present a framework for verifying Memoryful Neural Multi-Agent Systems (MN-MAS) against full Linear Temporal Logic (LTL) specifications. In MN-MAS, agents interact with a non-deterministic, partially observable environment. Examples of MN-MAS include multi-agent systems based on feed-forward and recurrent neural networks or state-space models. Different from previous approaches, we support the verification of both bounded and unbounded LTL specifications. We leverage well-established bounded model checking techniques, including lasso search and invariant synthesis, to reduce the verification problem to that of constraint solving. To solve these constraints, we develop efficient methods based on bound propagation, mixed-integer linear programming, and adaptive splitting. We evaluate the effectiveness of our algorithms in single and multi-agent environments from the Gymnasium and PettingZoo libraries, verifying unbounded specifications for the first time and improving the verification time for bounded specifications by an order of magnitude compared to the SoA.
format Preprint
id arxiv_https___arxiv_org_abs_2503_02512
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle LTL Verification of Memoryful Neural Agents
Hosseini, Mehran
Lomuscio, Alessio
Paoletti, Nicola
Logic in Computer Science
Artificial Intelligence
Machine Learning
Multiagent Systems
Symbolic Computation
68Q60 (Primary) 68T27, 68T07, 68T37, 68T40, 68T42 (Secondary)
D.2.4; F.3.1; I.2.4; I.2.11; I.2.8; F.4.1; I.2.2; I.2.3
We present a framework for verifying Memoryful Neural Multi-Agent Systems (MN-MAS) against full Linear Temporal Logic (LTL) specifications. In MN-MAS, agents interact with a non-deterministic, partially observable environment. Examples of MN-MAS include multi-agent systems based on feed-forward and recurrent neural networks or state-space models. Different from previous approaches, we support the verification of both bounded and unbounded LTL specifications. We leverage well-established bounded model checking techniques, including lasso search and invariant synthesis, to reduce the verification problem to that of constraint solving. To solve these constraints, we develop efficient methods based on bound propagation, mixed-integer linear programming, and adaptive splitting. We evaluate the effectiveness of our algorithms in single and multi-agent environments from the Gymnasium and PettingZoo libraries, verifying unbounded specifications for the first time and improving the verification time for bounded specifications by an order of magnitude compared to the SoA.
title LTL Verification of Memoryful Neural Agents
topic Logic in Computer Science
Artificial Intelligence
Machine Learning
Multiagent Systems
Symbolic Computation
68Q60 (Primary) 68T27, 68T07, 68T37, 68T40, 68T42 (Secondary)
D.2.4; F.3.1; I.2.4; I.2.11; I.2.8; F.4.1; I.2.2; I.2.3
url https://arxiv.org/abs/2503.02512