{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T16:49:40Z","timestamp":1784825380801,"version":"3.55.0"},"reference-count":36,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2023,12,1]],"date-time":"2023-12-01T00:00:00Z","timestamp":1701388800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,12,1]],"date-time":"2023-12-01T00:00:00Z","timestamp":1701388800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,12,1]],"date-time":"2023-12-01T00:00:00Z","timestamp":1701388800000},"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":["62062033"],"award-info":[{"award-number":["62062033"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004479","name":"Natural Science Foundation of Jiangxi Province","doi-asserted-by":"publisher","award":["20232BAB202018"],"award-info":[{"award-number":["20232BAB202018"]}],"id":[{"id":"10.13039\/501100004479","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004479","name":"Graduate Innovation Foundation of Jiangxi Province","doi-asserted-by":"publisher","award":["YC2022-s495"],"award-info":[{"award-number":["YC2022-s495"]}],"id":[{"id":"10.13039\/501100004479","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Intell. Transport. Syst."],"published-print":{"date-parts":[[2023,12]]},"DOI":"10.1109\/tits.2023.3302014","type":"journal-article","created":{"date-parts":[[2023,8,16]],"date-time":"2023-08-16T17:37:33Z","timestamp":1692207453000},"page":"14294-14305","source":"Crossref","is-referenced-by-count":17,"title":["Multi-Agent Mix Hierarchical Deep Reinforcement Learning for Large-Scale Fleet Management"],"prefix":"10.1109","volume":"24","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7269-4484","authenticated-orcid":false,"given":"Xiaohui","family":"Huang","sequence":"first","affiliation":[{"name":"School of Information Engineering, East China Jiaotong University, Nanchang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9681-8119","authenticated-orcid":false,"given":"Jiahao","family":"Ling","sequence":"additional","affiliation":[{"name":"School of Information Engineering, East China Jiaotong University, Nanchang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2458-6774","authenticated-orcid":false,"given":"Xiaofei","family":"Yang","sequence":"additional","affiliation":[{"name":"Department of Science and Technology, University of Macau, Macau, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiong","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Information Engineering, East China Jiaotong University, Nanchang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4604-1740","authenticated-orcid":false,"given":"Kaiming","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Information Engineering, East China Jiaotong University, Nanchang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/769800.769806"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-03404-1_11"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2019.00129"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3097983.3098138"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CEC48606.2020.9185858"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3128877"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3109611"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC48978.2021.9565029"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3357799"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3060187"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/RTSS52674.2021.00026"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3467979"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.3030252"},{"key":"ref14","article-title":"Deep dispatching: A deep reinforcement learning approach for vehicle dispatching on online ride-hailing platform","volume":"161","author":"Liu","year":"2022","journal-title":"Transp. Res. E, Logistics Transp. Rev."},{"issue":"129","key":"ref15","first-page":"1","article-title":"On the approximation of cooperative heterogeneous multi-agent reinforcement learning (MARL) using mean field control (MFC)","volume":"23","author":"Mondal","year":"2022","journal-title":"J. Mach. Learn. Res."},{"key":"ref16","first-page":"1371","article-title":"Can mean field control (MFC) approximate cooperative multi agent reinforcement learning (MARL) with non-uniform interaction?","volume-title":"Proc. 38th Conf. Uncertainty Artif. Intell.","volume":"180","author":"Mondal"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3308558.3313433"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3453160"},{"key":"ref19","first-page":"21579","article-title":"Generating adjacency-constrained subgoals in hierarchical reinforcement learning","volume-title":"Advances in Neural Information Processing Systems","volume":"33","author":"Zhang","year":"2020"},{"key":"ref20","doi-asserted-by":"crossref","DOI":"10.1016\/j.energy.2021.121703","article-title":"Hierarchical reinforcement learning based energy management strategy for hybrid electric vehicle","volume":"238","author":"Qi","year":"2022","journal-title":"Energy"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-30425-6_6"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2020.3038072"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2019.02.068"},{"key":"ref24","article-title":"Dynamics-aware unsupervised discovery of skills","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Sharma"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2019.01.011"},{"key":"ref26","first-page":"4344","article-title":"Learning by playing solving sparse reward tasks from scratch","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Riedmiller"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11902"},{"key":"ref28","first-page":"1515","article-title":"Automatic goal generation for reinforcement learning agents","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Florensa"},{"key":"ref29","article-title":"Hierarchical deep multiagent reinforcement learning with temporal abstraction","author":"Tang","year":"2018","journal-title":"arXiv:1809.09332"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC55140.2022.9922047"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3357978"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219993"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"issue":"1","key":"ref34","first-page":"7234","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":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2018.00077"},{"key":"ref36","first-page":"1995","article-title":"Dueling network architectures for deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wang"}],"container-title":["IEEE Transactions on Intelligent Transportation Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6979\/10339106\/10221776.pdf?arnumber=10221776","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T20:08:07Z","timestamp":1709323687000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10221776\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12]]},"references-count":36,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tits.2023.3302014","relation":{},"ISSN":["1524-9050","1558-0016"],"issn-type":[{"value":"1524-9050","type":"print"},{"value":"1558-0016","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,12]]}}}