Vulnerable Agent Identification In Large-scale Multi-agent Reinforcement Learning

Abstract

Partial agent failure becomes inevitable when systems scale up, making it crucial to identify the subset of agents whose compromise would most severely degrade overall performance. In this paper, 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 involves an NP-hard combinatorial task of selecting the most vulnerable agents, and the lower level learns worst-case adversarial policies for these agents using mean-field MARL. The two problems are coupled together, making HAD-MFC difficult to solve. To solve this, we first decouple the hierarchical process by Fenchel-Rockafellar transform, resulting a regularized mean-field Bellman operator for upper level that enables independent learning at each level, thus reducing computational complexity. We then reformulate the upper-level combinatorial problem as a MDP with den

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyli2025vulnerable

Related papers

• Risk-aware Distributed Multi-agent Reinforcement Learning (2023)3.58
• V-learning -- A Simple, Efficient, Decentralized Algorithm For Multiagent RL (2021)0.00
• Fault Tolerant Multi-agent Learning With Adversarial Budget Constraints (2025)0.00
• SUB-PLAY: Adversarial Policies Against Partially Observed Multi-agent Reinforcement Learning Systems (2024)0.00
• Attacking C-marl More Effectively: A Data Driven Approach (2022)0.00
• Interpretable Failure Analysis In Multi-agent Reinforcement Learning Systems (2026)0.00
• Major-minor Mean Field Multi-agent Reinforcement Learning (2023)0.00
• Camouflage Adversarial Attacks On Multiple Agent Systems (2024)0.00