Traditional robust methods in multi-agent reinforcement learning (MARL) often struggle against coordinated adversarial attacks in cooperative scenarios. To address this limitation, we propose the Wolfpack Adversarial Attack framework, inspired by wolf hunting strategies, which targets an initial agent and its assisting agents to disrupt cooperation. Additionally, we introduce the Wolfpack-Adversarial Learning for MARL (WALL) framework, which trains robust MARL policies to defend against the proposed Wolfpack attack by fostering systemwide collaboration. Experimental results underscore the devastating impact of the Wolfpack attack and the significant robustness improvements achieved by WALL. Our code is available at https://github.com/sunwoolee0504/WALL.
@article{arxiv.2502.02844,
title = {Wolfpack Adversarial Attack for Robust Multi-Agent Reinforcement Learning},
author = {Sunwoo Lee and Jaebak Hwang and Yonghyeon Jo and Seungyul Han},
journal= {arXiv preprint arXiv:2502.02844},
year = {2026}
}
Comments
9 pages main, 23 pages appendix with reference. Accepeted by ICML 2025