Enhancing the Robustness of QMIX against State-adversarial Attacks

TL;DR

This paper investigates methods to improve the robustness of the QMIX multi-agent reinforcement learning algorithm against state-adversarial attacks by training with diverse attacks and extending robustness techniques from single-agent to multi-agent settings.

Contribution

It introduces four techniques to enhance the robustness of QMIX against adversarial attacks and extends robustness strategies from single-agent to multi-agent reinforcement learning.

Findings

Training with diverse attacks improves robustness.

Techniques effectively extend to multi-agent scenarios.

Enhanced robustness demonstrated through experiments.

Abstract

Deep reinforcement learning (DRL) performance is generally impacted by state-adversarial attacks, a perturbation applied to an agent's observation. Most recent research has concentrated on robust single-agent reinforcement learning (SARL) algorithms against state-adversarial attacks. Still, there has yet to be much work on robust multi-agent reinforcement learning. Using QMIX, one of the popular cooperative multi-agent reinforcement algorithms, as an example, we discuss four techniques to improve the robustness of SARL algorithms and extend them to multi-agent scenarios. To increase the robustness of multi-agent reinforcement learning (MARL) algorithms, we train models using a variety of attacks in this research. We then test the models taught using the other attacks by subjecting them to the corresponding attacks throughout the training phase. In this way, we organize and summarize techniques for enhancing robustness when used with MARL.