CASIA OpenIR  > 学术期刊  > Machine Intelligence Research
Enhancing Multi-agent Coordination via Dual-channel Consensus
Qingyang Zhang1,2; Kaishen Wang1,3; Jingqing Ruan1,2; Yiming Yang1; Dengpeng Xing1,3; Bo Xu1,2,3
Source PublicationMachine Intelligence Research
ISSN2731-538X
2024
Volume21Issue:2Pages:349-368
AbstractSuccessful 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 consistency 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.
KeywordMulti-agent reinforcement learning, contrastive representation learning, consensus, multi-agent cooperation, cognitive consistency
DOI10.1007/s11633-023-1464-2
Citation statistics
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/56043
Collection学术期刊_Machine Intelligence Research
Affiliation1.Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China
2.School of Future Technology, University of Chinese Academy of Sciences, Beijing 100049, China
3.School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing 100049, China
First Author AffilicationInstitute of Automation, Chinese Academy of Sciences
Recommended Citation
GB/T 7714
Qingyang Zhang,Kaishen Wang,Jingqing Ruan,et al. Enhancing Multi-agent Coordination via Dual-channel Consensus[J]. Machine Intelligence Research,2024,21(2):349-368.
APA Qingyang Zhang,Kaishen Wang,Jingqing Ruan,Yiming Yang,Dengpeng Xing,&Bo Xu.(2024).Enhancing Multi-agent Coordination via Dual-channel Consensus.Machine Intelligence Research,21(2),349-368.
MLA Qingyang Zhang,et al."Enhancing Multi-agent Coordination via Dual-channel Consensus".Machine Intelligence Research 21.2(2024):349-368.
Files in This Item:
File Name/Size DocType Version Access License
MIR-2023-06-096.pdf(4997KB)期刊论文出版稿开放获取CC BY-NC-SAView
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Qingyang Zhang]'s Articles
[Kaishen Wang]'s Articles
[Jingqing Ruan]'s Articles
Baidu academic
Similar articles in Baidu academic
[Qingyang Zhang]'s Articles
[Kaishen Wang]'s Articles
[Jingqing Ruan]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Qingyang Zhang]'s Articles
[Kaishen Wang]'s Articles
[Jingqing Ruan]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: MIR-2023-06-096.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.