paper-with-me

홈 › Papers

On the Robustness of Cooperative Multi-Agent Reinforcement Learning

2020-03-08 · Jieyu Lin, Kristina Dzeparoska, Sai Qian Zhang, Alberto Leon-Garcia, Nicolas Papernot

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%.

📄 PDF Abstract BibTeX arXiv:2003.03722

Code (1)

dig-beihang/ami pytorch

Tasks

Multi-agent Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Similar Papers 제목 키워드 기반

Enhancing the Robustness of QMIX against State-adversarial Attacks

2023-07-03 · Weiran Guo, Guanjun Liu, Ziyuan Zhou, Ling Wang 외

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 reinforceme…

Deep Reinforcement LearningMulti-agent Reinforcement Learningreinforcement-learningReinforcement Learning

Evaluating Robustness of Cooperative MARL

2021-09-29 · Nhan Pham, Lam M. Nguyen, Jie Chen, Thanh Lam Hoang 외

In recent years, a proliferation of methods were developed for multi-agent reinforcement learning (MARL). In this paper, we focus on evaluating the robustness of MARL agents in continuous control tasks. In particular, we…

continuous-controlContinuous ControlMuJoCoMulti-agent Reinforcement Learning+2

Empirical Study on Robustness and Resilience in Cooperative Multi-Agent Reinforcement Learning

2025-10-13 · Simin Li, Zihao Mao, Hanxiao Li, Zonglei Jing 외 arxiv

In cooperative Multi-Agent Reinforcement Learning (MARL), it is a common practice to tune hyperparameters in ideal simulated environments to maximize cooperative performance. However, policies tuned for cooperation often…

Multi-agent Reinforcement Learning

Towards Comprehensive Testing on the Robustness of Cooperative Multi-agent Reinforcement Learning

2022-04-17 · Jun Guo, Yonghong Chen, Yihang Hao, Zixin Yin 외

While deep neural networks (DNNs) have strengthened the performance of cooperative multi-agent reinforcement learning (c-MARL), the agent policy can be easily perturbed by adversarial examples. Considering the safety cri…

ManagementMulti-agent Reinforcement Learningreinforcement-learningReinforcement Learning (RL)+2

Merging model-based control with multi-agent reinforcement learning for multi-agent cooperative teaming strategies

2026-06-04 · Christian Llanes, Spencer W. Jensen, Samuel Coogan arxiv

In this work, we propose a framework that combines multi-agent reinforcement learning (MARL) with model-based control to achieve safe, dynamically feasible actions in cooperative multi-agent tasks. Multi-agent reinforcem…

Multi-agent Reinforcement Learning