AI RESEARCH
COOL-MC: Verifying and Explaining RL Policies for Multi-bridge Network Maintenance
arXiv CS.LG
•
ArXi:2603.07546v1 Announce Type: cross Aging bridge networks require proactive, verifiable, and interpretable maintenance strategies, yet reinforcement learning (RL) policies trained solely on reward signals provide no formal safety guarantees and remain opaque to infrastructure managers.