Group-Aware Coordination Graph for Multi-Agent Reinforcement Learning

[2404.10976] Group-Aware Coordination Graph for Multi-Agent Reinforcement Learning Skip to main content Search Submit Donate Log in Search arXiv Press Enter to search · Advanced search Computer Science > Machine Learning arXiv:2404.10976 (cs) [Submitted on 17 Apr 2024 ( v1 ), last revised 10 Apr 2026 (this version, v4)] Title: Group-Aware Coordination Graph for Multi-Agent Reinforcement Learning Authors: Wei Duan , Jie Lu , Junyu Xuan View a PDF of the paper titled Group-Aware Coordination Graph for Multi-Agent Reinforcement Learning, by Wei Duan and 2 other authors View PDF HTML (experimental) Abstract: Cooperative Multi-Agent Reinforcement Learning (MARL) necessitates seamless collaboration among agents, often represented by an underlying relation graph. Existing methods for learning this graph primarily focus on agent-pair relations, neglecting higher-order relationships. While several approaches attempt to extend cooperation modelling to encompass behaviour similarities within groups, they commonly fall short in concurrently learning the latent graph, thereby constraining the information exchange among partially observed agents. To overcome these limitations, we present a novel approach to infer the Group-Aware Coordination Graph (GACG), which is designed to capture both the cooperation between agent pairs based on current observations and group-level dependencies from behaviour patterns observed across trajectories. This graph is further used in graph convolution for information exchange between agents during decision-making. To further ensure behavioural consistency among agents within the same group, we introduce a group distance loss, which promotes group cohesion and encourages specialization between groups. Our evaluations, conducted on StarCraft II micromanagement tasks, demonstrate GACG's superior performance. An ablation study further provides experimental evidence of the effectiveness of each component of our method. Comments: Accepted by IJCAI 2024. Update Discussion Subjects: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI); Multiagent Systems (cs.MA) Cite as: arXiv:2404.10976 [cs.LG] (or arXiv:2404.10976v4 [cs.LG] for this version) https://doi.org/10.48550/arXiv.2404.10976 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Wei Duan [ view email ] [v1] Wed, 17 Apr 2024 01:17:10 UTC (497 KB) [v2] Sat, 20 Apr 2024 05:04:02 UTC (498 KB) [v3] Sat, 11 May 2024 23:50:21 UTC (498 KB) [v4] Fri, 10 Apr 2026 00:30:36 UTC (507 KB) Full-text links: Access Paper: View a PDF of the paper titled Group-Aware Coordination Graph for Multi-Agent Reinforcement Learning, by Wei Duan and 2 other authors View PDF HTML (experimental) TeX Source view license Current browse context: cs.LG < prev | next > new | recent | 2024-04 Change to browse by: cs cs.AI cs.MA References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) IArxiv recommender toggle IArxiv Recommender ( What is IArxiv? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab) Major funding support from

Related documents

• When Agents Coordinate: Measuring Coordination in Multi-Agent AI Coding#625354
• When Agents Coordinate: Measuring Coordination in Multi-Agent AI Coding#623081
• When Agents Coordinate: Measuring Coordination in Multi-Agent AI Coding#459696
• Coordination Games over Belief–Action Geometry: Structural Limits of Coordination under Representational Incompatibility#118184
• Language-model groups overstate consensus when replaying human deliberation on a reasoning task#1034357