{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T20:06:24Z","timestamp":1780949184649,"version":"3.54.1"},"reference-count":31,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012659","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62263017"],"award-info":[{"award-number":["62263017"]}],"id":[{"id":"10.13039\/501100012659","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Science and Technology Talent and Platform Program of Yunnan Province, China","award":["202505AT350001"],"award-info":[{"award-number":["202505AT350001"]}]},{"name":"Basic Research Program Project of Yunnan Province, China","award":["202301AU070059"],"award-info":[{"award-number":["202301AU070059"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2026,5]]},"DOI":"10.1109\/lra.2026.3669783","type":"journal-article","created":{"date-parts":[[2026,3,3]],"date-time":"2026-03-03T20:54:17Z","timestamp":1772571257000},"page":"5278-5285","source":"Crossref","is-referenced-by-count":0,"title":["Mean-Field Deep Reinforcement Learning for Multi-Agent Path Finding"],"prefix":"10.1109","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6510-5212","authenticated-orcid":false,"given":"Lin","family":"Huo","sequence":"first","affiliation":[{"name":"Faculty of Mechanical and Electrical Engineering, Kunming University of Science and Technology, Kunming, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1407-4863","authenticated-orcid":false,"given":"Jianlin","family":"Mao","sequence":"additional","affiliation":[{"name":"Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4256-5582","authenticated-orcid":false,"given":"Hongjun","family":"San","sequence":"additional","affiliation":[{"name":"Faculty of Mechanical and Electrical Engineering, Kunming University of Science and Technology, Kunming, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8934-8032","authenticated-orcid":false,"given":"Ruiqi","family":"Li","sequence":"additional","affiliation":[{"name":"Faculty of Mechanical and Electrical Engineering, Kunming University of Science and Technology, Kunming, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhiwei","family":"Xuan","sequence":"additional","affiliation":[{"name":"Faculty of Mechanical and Electrical Engineering, Kunming University of Science and Technology, Kunming, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1609\/socs.v17i1.31565"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2022.3158425"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2022.103662"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3102140"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/BF01386390"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2025.110978"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.aei.2024.102523"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/iros58592.2024.10802643"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2025.3598399"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2023.124173"},{"key":"ref11","article-title":"Scalability bottlenecks in multi-agent reinforcement learning systems","author":"Gogineni","year":"2023"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2903261"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3062803"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2024.3379048"},{"key":"ref15","first-page":"24611","article-title":"The surprising effectiveness of PPO in cooperative multi-agent games","volume":"35","author":"Yu","year":"2022","journal-title":"in Proc. Adv. Neural Inf. Process. Syst."},{"key":"ref16","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"ref17","article-title":"Curriculum learning for cooperation in multi-agent reinforcement learning","volume-title":"Proc. 37th Conf. Neural Inf. Process. Syst.","author":"Bhati","year":"2023"},{"key":"ref18","first-page":"10707","article-title":"Sharedexperience actor-critic for multi-agent reinforcement learning","volume":"33","author":"Christianos","year":"2020","journal-title":"in Proc. Adv. Neural Inf. Process. Syst."},{"key":"ref19","first-page":"12078","article-title":"Scalable deep reinforcement learning algorithms for mean field games","volume-title":"Proc. 39th IEEE Int. Conf. Mach. Learn.","author":"Lauriere","year":"2022"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.jfranklin.2023.09.002"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-56436-4"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.3390\/drones7070476"},{"key":"ref23","first-page":"5571","article-title":"Mean field multi-agent reinforcement learning","volume-title":"Proc. 35th IEEE Int. Conf. Mach. Learn.","author":"Yang","year":"2018"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989037"},{"issue":"129","key":"ref25","first-page":"1","article-title":"On the approximation of cooperative heterogeneous multi-agent reinforcement learning using mean field control","volume":"23","author":"Mondal","year":"2022","journal-title":"J. Mach. Learn. Res."},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2024.3522370"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.53469\/jtpes.2024.04(04).07"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN48605.2020.9206879"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3111321"},{"key":"ref30","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"Proc. 35th IEEE Int. Conf. Mach. Learn.","author":"Fujimoto","year":"2018"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1609\/socs.v10i1.18510"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7083369\/11435997\/11419785.pdf?arnumber=11419785","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T19:53:46Z","timestamp":1780948426000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11419785\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5]]},"references-count":31,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/lra.2026.3669783","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5]]}}}