{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T15:56:01Z","timestamp":1759334161679,"version":"build-2065373602"},"reference-count":29,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,8,17]],"date-time":"2025-08-17T00:00:00Z","timestamp":1755388800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,8,17]],"date-time":"2025-08-17T00:00:00Z","timestamp":1755388800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,8,17]]},"DOI":"10.1109\/case58245.2025.11163947","type":"proceedings-article","created":{"date-parts":[[2025,9,23]],"date-time":"2025-09-23T17:24:07Z","timestamp":1758648247000},"page":"650-655","source":"Crossref","is-referenced-by-count":0,"title":["Group-Based QMIX for Multi-Agent Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Weixin","family":"Hong","sequence":"first","affiliation":[{"name":"Chinese Academy of Sciences,State Key Laboratory of Multimodal Artificial Intelligence Systems, Beijing Engineering Research Center of Intelligent Systems and Technology, Institute of Automation,Beijing,China,100190"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huaiyu","family":"Wu","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,State Key Laboratory of Multimodal Artificial Intelligence Systems, Beijing Engineering Research Center of Intelligent Systems and Technology, Institute of Automation,Beijing,China,100190"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"He","family":"Fang","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,State Key Laboratory of Multimodal Artificial Intelligence Systems, Beijing Engineering Research Center of Intelligent Systems and Technology, Institute of Automation,Beijing,China,100190"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhen","family":"Shen","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,State Key Laboratory of Multimodal Artificial Intelligence Systems, Beijing Engineering Research Center of Intelligent Systems and Technology, Institute of Automation,Beijing,China,100190"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yunjun","family":"Han","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,State Key Laboratory of Multimodal Artificial Intelligence Systems, Beijing Engineering Research Center of Intelligent Systems and Technology, Institute of Automation,Beijing,China,100190"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yisheng","family":"Lv","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,State Key Laboratory of Multimodal Artificial Intelligence Systems, Beijing Engineering Research Center of Intelligent Systems and Technology, Institute of Automation,Beijing,China,100190"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gang","family":"Xiong","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,State Key Laboratory of Multimodal Artificial Intelligence Systems, Beijing Engineering Research Center of Intelligent Systems and Technology, Institute of Automation,Beijing,China,100190"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.3390\/electronics14040820"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/GLOBECOM46510.2021.9685941"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3269206.3272021"},{"article-title":"An introduction to centralized training for decentralized execution in cooperative multi-agent reinforcement learning","year":"2024","author":"Amato","key":"ref4"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-307-3.50049-6"},{"article-title":"Value-decomposition networks for cooperative multi-agent learning","year":"2017","author":"Sunehag","key":"ref6"},{"issue":"178","key":"ref7","first-page":"1","article-title":"Monotonic value function factorisation for deep multiagent reinforcement learning","volume":"21","author":"Rashid","year":"2020","journal-title":"Journal of Machine Learning Research"},{"key":"ref8","first-page":"5887","article-title":"Qtran: Learning to factorize with transformation for cooperative multi-agent reinforcement learning","volume-title":"International Conference on Machine Learning","author":"Son"},{"article-title":"Qatten: A general framework for cooperative multiagent reinforcement learning","year":"2020","author":"Yang","key":"ref9"},{"key":"ref10","article-title":"Maven: Multi-agent variational exploration","volume":"32","author":"Mahajan","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref11","first-page":"1365","article-title":"Regularized softmax deep multi-agent q-learning","volume":"34","author":"Pan","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref12","first-page":"10706","article-title":"Q-value path decomposition for deep multiagent reinforcement learning","volume-title":"International Conference on Machine Learning","author":"Yang"},{"key":"ref13","first-page":"1995","article-title":"Dueling network architectures for deep reinforcement learning","volume-title":"International Conference on Machine Learning","author":"Wang"},{"key":"ref14","first-page":"980","article-title":"Deep coordination graphs","volume-title":"International Conference on Machine Learning","author":"B\u00f6hmer"},{"key":"ref15","first-page":"24018","article-title":"Vast: Value function factorization with variable agent subteams","volume":"34","author":"Phan","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref16","article-title":"Meta-gradient reinforcement learning","volume":"31","author":"Xu","year":"2018","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref17","first-page":"4596","article-title":"Randomized entity-wise factorization for multi-agent reinforcement learning","volume-title":"International Conference on Machine Learning","author":"Iqbal"},{"article-title":"Roma: Multiagent reinforcement learning with emergent roles","year":"2020","author":"Wang","key":"ref18"},{"article-title":"Rode: Learning roles to decompose multi-agent tasks","year":"2020","author":"Wang","key":"ref19"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.3390\/machines12010008"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-28929-8"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1017\/S0269888912000057"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.physd.2019.132306"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-023-00876-4"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3331184.3331214"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1186\/s13321-020-00460-5"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-019-0024-5"},{"article-title":"Graph attention networks","year":"2017","author":"Veli\u010dkovi\u0107","key":"ref28"},{"key":"ref29","first-page":"10199","article-title":"Weighted qmix: Expanding monotonic value function factorisation for deep multi-agent reinforcement learning","volume":"33","author":"Rashid","year":"2020","journal-title":"Advances in Neural Information Processing Systems"}],"event":{"name":"2025 IEEE 21st International Conference on Automation Science and Engineering (CASE)","start":{"date-parts":[[2025,8,17]]},"location":"Los Angeles, CA, USA","end":{"date-parts":[[2025,8,21]]}},"container-title":["2025 IEEE 21st International Conference on Automation Science and Engineering (CASE)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11163731\/11163732\/11163947.pdf?arnumber=11163947","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,30]],"date-time":"2025-09-30T13:19:30Z","timestamp":1759238370000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11163947\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,17]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/case58245.2025.11163947","relation":{},"subject":[],"published":{"date-parts":[[2025,8,17]]}}}