Enhancing the Robustness of QMIX against State-adversarial Attacks

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, the...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2023-07
Main Authors: Guo, Weiran, Liu, Guanjun, Zhou, Ziyuan, Wang, Ling, Wang, Jiacun
Format: Article
Language:English
Subjects:
Algorithms
Deep learning
Machine learning
Multiagent systems
Perturbation
Robustness
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:2331-8422
DOI:10.48550/arxiv.2307.00907