LGAICRMAFeb 5, 2025

Wolfpack Adversarial Attack for Robust Multi-Agent Reinforcement Learning

arXiv:2502.02844v35 citationsh-index: 1Has CodeICML
Originality Incremental advance
AI Analysis

This addresses vulnerabilities in multi-agent systems for applications like robotics or autonomous vehicles, though it appears incremental as it builds on existing robust MARL methods.

The paper tackles the problem of coordinated adversarial attacks in cooperative multi-agent reinforcement learning by proposing the Wolfpack Adversarial Attack framework to disrupt cooperation and the WALL framework to defend against it, resulting in significant robustness improvements.

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.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes