Wolfpack Adversarial Attack for Robust Multi-Agent Reinforcement Learning

TL;DR

This paper introduces the Wolfpack Adversarial Attack framework to disrupt cooperative multi-agent reinforcement learning and proposes WALL, a training method to enhance robustness against such attacks, demonstrated by experimental results.

Contribution

The paper presents a novel Wolfpack attack strategy and a corresponding defense training framework, improving robustness in multi-agent reinforcement learning against coordinated adversarial attacks.

Findings

Wolfpack attack significantly disrupts cooperative MARL systems.

WALL training enhances robustness against Wolfpack attacks.

Experimental results show improved system resilience.

Abstract

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.