首页|Enhancing Multi-agent Coordination via Dual-channel Consensus

Enhancing Multi-agent Coordination via Dual-channel Consensus

扫码查看
原文链接
  • NETL
  • NSTL
  • 万方数据
Successful coordination in multi-agent systems requires agents to achieve consensus.Previous works propose methods through information sharing,such as explicit information sharing via communication protocols or exchanging information implicitly via behavior prediction.However,these methods may fail in the absence of communication channels or due to biased modeling.In this work,we propose to develop dual-channel consensus(DuCC)via contrastive representation learning for fully cooperative multi-agent systems,which does not need explicit communication and avoids biased modeling.DuCC comprises two types of consensus:temporally extended consensus within each agent(inner-agent consensus)and mutual consensus across agents(inter-agent consensus).To achieve DuCC,we design two objectives to learn representations of slow environmental features for inner-agent consensus and to realize cognitive consist-ency as inter-agent consensus.Our DuCC is highly general and can be flexibly combined with various MARL algorithms.The extensive experiments on StarCraft multi-agent challenge and Google research football demonstrate that our method efficiently reaches consensus and performs superiorly to state-of-the-art MARL algorithms.

Multi-agent reinforcement learningcontrastive representation learningconsensusmulti-agent cooperationcognitive consistency

Qingyang Zhang、Kaishen Wang、Jingqing Ruan、Yiming Yang、Dengpeng Xing、Bo Xu

展开 >

Institute of Automation,Chinese Academy of Sciences,Beijing 100190,China

School of Future Technology,University of Chinese Academy of Sciences,Beijing 100049,China

School of Artificial Intelligence,University of Chinese Academy of Sciences,Beijing 100049,China

Strategic Priority Research Program of the Chinese Academy of Sciences,ChinaProgram for National Nature Science Foundation of China

XDA2703030062073324

2024

10.1007/s11633-023-1464-2

机器智能研究(英文)
中国科学院自动化所

机器智能研究(英文)

CSTPCDEI
影响因子：0.49
ISSN：2731-538X
年,卷(期)：2024.21(2)
  • 73