On the Robustness of Cooperative Multi-Agent Reinforcement Learning

被引:32
|
作者
Lin, Jieyu [1 ]
Dzeparoska, Kristina [1 ]
Zhang, Sai Qian [2 ]
Leon-Garcia, Alberto [1 ]
Papernot, Nicolas [1 ,3 ]
机构
[1] Univ Toronto, Toronto, ON, Canada
[2] Harvard Univ, Cambridge, MA 02138 USA
[3] Vector Inst, Toronto, ON, Canada
关键词
D O I
10.1109/SPW50608.2020.00027
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
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%.
引用
收藏
页码:62 / 68
页数:7
相关论文
共 50 条
  • [1] Towards Comprehensive Testing on the Robustness of Cooperative Multi-agent Reinforcement Learning
    Guo, Jun
    Chen, Yonghong
    Hao, Yihang
    Yin, Zixin
    Yu, Yin
    Li, Simin
    [J]. 2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS, CVPRW 2022, 2022, : 114 - 121
  • [2] Multi-Agent Uncertainty Sharing for Cooperative Multi-Agent Reinforcement Learning
    Chen, Hao
    Yang, Guangkai
    Zhang, Junge
    Yin, Qiyue
    Huang, Kaiqi
    [J]. 2022 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2022,
  • [3] Consensus Learning for Cooperative Multi-Agent Reinforcement Learning
    Xu, Zhiwei
    Zhang, Bin
    Li, Dapeng
    Zhang, Zeren
    Zhou, Guangchong
    Chen, Hao
    Fan, Guoliang
    [J]. THIRTY-SEVENTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, VOL 37 NO 10, 2023, : 11726 - 11734
  • [4] Learning Cooperative Intrinsic Motivation in Multi-Agent Reinforcement Learning
    Hong, Seung-Jin
    Lee, Sang-Kwang
    [J]. 12TH INTERNATIONAL CONFERENCE ON ICT CONVERGENCE (ICTC 2021): BEYOND THE PANDEMIC ERA WITH ICT CONVERGENCE INNOVATION, 2021, : 1697 - 1699
  • [5] Cooperative Learning of Multi-Agent Systems Via Reinforcement Learning
    Wang, Xin
    Zhao, Chen
    Huang, Tingwen
    Chakrabarti, Prasun
    Kurths, Juergen
    [J]. IEEE TRANSACTIONS ON SIGNAL AND INFORMATION PROCESSING OVER NETWORKS, 2023, 9 : 13 - 23
  • [6] Cooperative Multi-Agent Reinforcement Learning with Hypergraph Convolution
    Bai, Yunpeng
    Gong, Chen
    Zhang, Bin
    Fan, Guoliang
    Hou, Xinwen
    Lu, Yu
    [J]. 2022 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2022,
  • [7] Multi-agent Cooperative Search based on Reinforcement Learning
    Sun, Yinjiang
    Zhang, Rui
    Liang, Wenbao
    Xu, Cheng
    [J]. PROCEEDINGS OF 2020 3RD INTERNATIONAL CONFERENCE ON UNMANNED SYSTEMS (ICUS), 2020, : 891 - 896
  • [8] Cooperative Multi-Agent Reinforcement Learning With Approximate Model Learning
    Park, Young Joon
    Lee, Young Jae
    Kim, Seoung Bum
    [J]. IEEE ACCESS, 2020, 8 : 125389 - 125400
  • [9] Multi-agent cooperative learning research based on reinforcement learning
    Liu, Fei
    Zeng, Guangzhou
    [J]. 2006 10TH INTERNATIONAL CONFERENCE ON COMPUTER SUPPORTED COOPERATIVE WORK IN DESIGN, PROCEEDINGS, VOLS 1 AND 2, 2006, : 1408 - 1413
  • [10] A review of cooperative multi-agent deep reinforcement learning
    Oroojlooy, Afshin
    Hajinezhad, Davood
    [J]. APPLIED INTELLIGENCE, 2023, 53 (11) : 13677 - 13722