Paper Info
Title
On the Robustness of Cooperative Multi-Agent Reinforcement Learning
Abstract
In cooperative multi-agent reinforcement learning (c-MARL), agents learn to cooperatively take actions as a team to maximize a total team reward. We analyze the robustness of c-MARL to adversaries capable of attacking one of the agents on a team. Through the ability to manipulate this agent's observations, the adversary seeks to decrease the total team reward. Attacking c-MARL is challenging for three reasons: first, it is difficult to estimate team rewards or how they are impacted by an agent mispredicting; second, models are non-differentiable; and third, the feature space is low-dimensional. Thus, we introduce a novel attack. The attacker first trains a policy network with reinforcement learning to find a wrong action it should encourage the victim agent to take. Then, the adversary uses targeted adversarial examples to force the victim to take this action. Our results on the StartCraft II multi-agent benchmark demonstrate that c-MARL teams are highly vulnerable to perturbations applied to one of their agent's observations. By attacking a single agent, our attack method has highly negative impact on the overall team reward, reducing it from 20 to 9.4. This results in the team's winning rate to go down from 98.9% to 0%.
Year
DOI
Venue
2020
10.1109/SPW50608.2020.00027
2020 IEEE Security and Privacy Workshops (SPW)
Keywords
DocType
ISBN
machine learning,Cooperative Multi Agent Reinforcement Learning,Adversarial Examples,Adversarial Policy,Robustness,Deep reinforcement learning,Q Learning
Conference
978-1-7281-9347-2
Citations 
PageRank 
References 
4
0.45
4
Authors
5
Name
Order
Citations
PageRank
Jieyu Lin1142.12
Dzeparoska Kristina240.45
Sai Zhang3557.79
Alberto Leon-Garcia41718264.79
Nicolas Papernot5193287.62