{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T16:39:47Z","timestamp":1783096787495,"version":"3.54.6"},"reference-count":33,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T00:00:00Z","timestamp":1725148800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["52302481"],"award-info":[{"award-number":["52302481"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Wuyi University's Hong Kong and Macao Joint Research and Development Fund","award":["2019WGALH15"],"award-info":[{"award-number":["2019WGALH15"]}]},{"name":"Wuyi University's Hong Kong and Macao Joint Research and Development Fund","award":["2019WGALH17"],"award-info":[{"award-number":["2019WGALH17"]}]},{"name":"Wuyi University's Hong Kong and Macao Joint Research and Development Fund","award":["2021WGALH15"],"award-info":[{"award-number":["2021WGALH15"]}]},{"name":"Innovation and Technology Commission of Hong Kong SAR Government, China","award":["K-BBY1"],"award-info":[{"award-number":["K-BBY1"]}]},{"name":"Chengdu Guojia Electrical Engineering Company, Ltd","award":["NEEC-2022-B13"],"award-info":[{"award-number":["NEEC-2022-B13"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Veh. Technol."],"published-print":{"date-parts":[[2024,9]]},"DOI":"10.1109\/tvt.2024.3391279","type":"journal-article","created":{"date-parts":[[2024,4,19]],"date-time":"2024-04-19T17:23:19Z","timestamp":1713547399000},"page":"12747-12759","source":"Crossref","is-referenced-by-count":14,"title":["Cooperative Control of Maglev Levitation System via Hamilton\u2013Jacobi\u2013Bellman Multi-Agent Deep Reinforcement Learning"],"prefix":"10.1109","volume":"73","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7801-2672","authenticated-orcid":false,"given":"Qi","family":"Zhu","sequence":"first","affiliation":[{"name":"Department of Civil and Environmental Engineering, The Hong Kong Polytechnic University, Kowloon, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1285-1553","authenticated-orcid":false,"given":"Su-Mei","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Civil and Environmental Engineering, The Hong Kong Polytechnic University, Kowloon, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1527-7777","authenticated-orcid":false,"given":"Yi-Qing","family":"Ni","sequence":"additional","affiliation":[{"name":"Department of Civil and Environmental Engineering, The Hong Kong Polytechnic University, Kowloon, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Theory and Technology For Improving High-Speed Railway Transportation Capacity","author":"Wang","year":"2023"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/tmag.2006.875842"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-94-017-7524-3"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/access.2018.2861885"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/access.2020.3024665"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-38077-9_102"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.3390\/electronics10030332"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/icca.2013.6564922"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1002\/aic.10520"},{"key":"ref10","volume-title":"Process Control Systems: Application, Design, and Tuning","author":"Greg. Shinskey","year":"1996"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/S0019-0578(97)00008-6"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.3233\/jae-190005"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11794"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467420"},{"key":"ref15","article-title":"Learning to communicate with deep multi-agent reinforcement learning","volume":"29","author":"Foerster","year":"2016","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref16","article-title":"Learning multiagent communication with backpropagation","volume":"29","author":"Sukhbaatar","year":"2016","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref17","first-page":"6380","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume-title":"Proc. 31st Int. Conf. Neural Inf. Process. Syst.","author":"Lowe"},{"key":"ref18","first-page":"24611","article-title":"The surprising effectiveness of ppo in cooperative, multi-agent games","volume":"35","author":"Yu","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2016.11.008"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC55140.2022.9922205"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1155\/2015\/865650"},{"key":"ref22","article-title":"Deep reinforcement learning: An overview","author":"Li","year":"2017"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1137\/s0363012901385691"},{"key":"ref24","article-title":"Highdimensional continuous control using generalized advantage estimation","volume-title":"arXiv.org","author":"Schulman"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2008.02.003"},{"key":"ref26","article-title":"Equivalence between policy gradients and soft Q-learning","author":"Schulman","year":"2017"},{"key":"ref27","first-page":"1","article-title":"PGQ: Combining policy gradient and Q-learning","volume-title":"Proc. 5th Int. Conf. Learn. Representations","author":"ODonoghue"},{"key":"ref28","first-page":"1","article-title":"Q-Prop: Sample-efficient policy gradient with an offpolicy critic","volume-title":"Proc. 5th Int. Conf. Learn. Representations","author":"Gu"},{"key":"ref29","first-page":"1","article-title":"Deterministic policy gradient algorithms","volume-title":"Proc. 31st Int. Conf. Mach. Learn.","author":"Silver"},{"key":"ref30","first-page":"1","article-title":"Continuous control with deep reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Lillicrap"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/access.2019.2940053"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-94-017-7524-3"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.jsv.2004.06.032"}],"container-title":["IEEE Transactions on Vehicular Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/25\/10683799\/10505742.pdf?arnumber=10505742","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,15]],"date-time":"2025-01-15T19:50:42Z","timestamp":1736970642000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10505742\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9]]},"references-count":33,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tvt.2024.3391279","relation":{},"ISSN":["0018-9545","1939-9359"],"issn-type":[{"value":"0018-9545","type":"print"},{"value":"1939-9359","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,9]]}}}