AI RESEARCH
Vulnerable Agent Identification in Large-Scale Multi-Agent Reinforcement Learning
arXiv CS.AI
•
ArXi:2509.15103v3 Announce Type: replace-cross Partial agent failure becomes inevitable when systems scale up, making it crucial to identify the subset of agents whose failure causes worst-case system performance degradations. We study this Vulnerable Agent Identification (VAI) problem in large-scale multi-agent reinforcement learning (MARL). We frame VAI as a Hierarchical Adversarial Decentralized Mean Field Control (HAD-MFC), where the upper level selects vulnerable agents as an NP-hard task and the lower level learns their worst-case adversarial policies via mean-field.