{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,6]],"date-time":"2025-05-06T04:06:47Z","timestamp":1746504407135,"version":"3.40.4"},"reference-count":23,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"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","award":["62473290","62088101"],"award-info":[{"award-number":["62473290","62088101"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2025,6]]},"DOI":"10.1109\/lra.2025.3559828","type":"journal-article","created":{"date-parts":[[2025,4,10]],"date-time":"2025-04-10T17:19:26Z","timestamp":1744305566000},"page":"5967-5974","source":"Crossref","is-referenced-by-count":0,"title":["Self-Organised Sequential Multi-Agent Reinforcement Learning for Closely Cooperation Tasks"],"prefix":"10.1109","volume":"10","author":[{"given":"Hao","family":"Fu","sequence":"first","affiliation":[{"name":"College of Electronic and Information Engineering, Tongji University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2758-167X","authenticated-orcid":false,"given":"Mingyu","family":"You","sequence":"additional","affiliation":[{"name":"College of Electronic and Information Engineering, Tongji University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6256-2485","authenticated-orcid":false,"given":"Hongjun","family":"Zhou","sequence":"additional","affiliation":[{"name":"College of Electronic and Information Engineering, Tongji University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3193-6269","authenticated-orcid":false,"given":"Bin","family":"He","sequence":"additional","affiliation":[{"name":"College of Electronic and Information Engineering, Tongji University, Shanghai, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3250269"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-60990-0_12"},{"key":"ref3","first-page":"1089","article-title":"Improved cooperative multi-agent reinforcement learning algorithm augmented by mixing demonstrations from centralized policy","volume-title":"Proc. 18th Int. Conf. Auton. Agents MultiAgent Syst.","author":"Lee","year":"2019"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-27645-3"},{"key":"ref5","first-page":"2137","article-title":"Learning to communicate with deep multi-agent reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"29","author":"Foerster","year":"2016"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-022-04105-y"},{"key":"ref7","first-page":"6379","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Lowe","year":"2017"},{"key":"ref8","first-page":"24611","article-title":"The surprising effectiveness of ppo in cooperative multi-agent games","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Yu","year":"2022"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2023.3293193"},{"article-title":"Value-decomposition networks for cooperative multi-agent learning","year":"2017","author":"Sunehag","key":"ref10"},{"issue":"178","key":"ref11","first-page":"1","article-title":"Monotonic value function factorisation for deep multi-agent reinforcement learning","volume":"21","author":"Rashid","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref12","first-page":"5887","article-title":"Qtran: Learning to factorize with transformation for cooperative multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Son","year":"2019"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.simpat.2014.06.005"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/2644819"},{"issue":"PMLR","key":"ref15","first-page":"9876","article-title":"Roma: Multi-agent reinforcement learning with emergent roles","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wang","year":"2020"},{"key":"ref16","first-page":"1","article-title":"Rode: Learning roles to decompose multi- agent tasks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wang","year":"2021"},{"key":"ref17","first-page":"24018","article-title":"Vast: Value function factorization with variable agent sub-teams","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Phan","year":"2021"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-16-5164-9_5"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref20","article-title":"Graph attention networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Velikovi","year":"2018"},{"article-title":"Proximal policy optimization algorithms","year":"2017","author":"Schulman","key":"ref21"},{"issue":"3","key":"ref22","first-page":"419","article-title":"Prim\u2019s algorithm for solving minimum spanning tree problem in fuzzy environment","volume":"12","author":"Dey","year":"2016","journal-title":"Ann. Fuzzy Math. Informat."},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/1187436.1216585"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7083369\/10969146\/10960625.pdf?arnumber=10960625","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,5]],"date-time":"2025-05-05T17:58:56Z","timestamp":1746467936000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10960625\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6]]},"references-count":23,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/lra.2025.3559828","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"type":"electronic","value":"2377-3766"},{"type":"electronic","value":"2377-3774"}],"subject":[],"published":{"date-parts":[[2025,6]]}}}