{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,13]],"date-time":"2026-02-13T21:38:17Z","timestamp":1771018697999,"version":"3.50.1"},"reference-count":50,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":["62203350"],"award-info":[{"award-number":["62203350"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62373297"],"award-info":[{"award-number":["62373297"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100015401","name":"Key Research and Development Projects of Shaanxi Province","doi-asserted-by":"publisher","award":["2022GY-033"],"award-info":[{"award-number":["2022GY-033"]}],"id":[{"id":"10.13039\/501100015401","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100013993","name":"Xi\u2019an Jiaotong University Research Fund for AI Science","doi-asserted-by":"publisher","award":["2025YXYC004"],"award-info":[{"award-number":["2025YXYC004"]}],"id":[{"id":"10.13039\/501100013993","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Automat. Sci. Eng."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tase.2026.3651287","type":"journal-article","created":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T22:04:57Z","timestamp":1768255497000},"page":"4068-4087","source":"Crossref","is-referenced-by-count":0,"title":["Safe and Scalable Multi-Agent Optimization for Autonomous Electric Taxi Dispatching via a Two-Stage Reinforcement Learning Framework"],"prefix":"10.1109","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-8416-6193","authenticated-orcid":false,"given":"Meng","family":"Zhao","sequence":"first","affiliation":[{"name":"School of Automation Science and Engineering, Xi’an Jiaotong University, Xi’an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanbin","family":"Zou","sequence":"additional","affiliation":[{"name":"School of Automation Science and Engineering, Xi’an Jiaotong University, Xi’an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-7167-3017","authenticated-orcid":false,"given":"Junyi","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Automation Science and Engineering, Xi’an Jiaotong University, Xi’an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6976-0727","authenticated-orcid":false,"given":"Donghe","family":"Li","sequence":"additional","affiliation":[{"name":"MOE Key Laboratory for Intelligent Networks and Network Security and the School of Automation Science and Engineering, Xi’an Jiaotong University, Xi’an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1525-2900","authenticated-orcid":false,"given":"Qingyu","family":"Yang","sequence":"additional","affiliation":[{"name":"SKLMSE Laboratory and the School of Automation Science and Engineering, Xi’an Jiaotong University, Xi’an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"issue":"3","key":"ref1","first-page":"383","article-title":"The uber-all economy of the future","volume":"20","author":"Smith","year":"2016","journal-title":"Independ. Rev."},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2020.102844"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2024.124706"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/LCSYS.2020.3046995"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2018.8485988"},{"key":"ref6","article-title":"Optimizing online matching for ride-sourcing services with multi-agent deep reinforcement learning","author":"Ke","year":"2019","journal-title":"arXiv:1902.06228"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.mex.2024.103037"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1111\/mice.12157"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2020.2990397"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.egyr.2022.02.029"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2022.103792"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3092276"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CCNC.2019.8651730"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.trd.2019.09.021"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2022.3178819"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.omega.2021.102448"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1287\/trsc.2022.1188"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2020.3022173"},{"key":"ref19","article-title":"SUNRISE: A simple unified framework for ensemble learning in deep reinforcement learning","author":"Lee","year":"2021","journal-title":"arXiv:2007.04938"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2020.3025082"},{"key":"ref21","first-page":"4295","article-title":"QMix: Monotonic value function factorisation for deep multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Rashid"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2103.01955"},{"key":"ref23","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"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.3390\/su151813553"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/MITS.2019.2962159"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2019.2947408"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aiide.v15i1.5222"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2016.7508798"},{"key":"ref29","article-title":"Reinforcement learning with unsupervised auxiliary tasks","author":"Jaderberg","year":"2016","journal-title":"arXiv:1611.05397"},{"key":"ref30","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","author":"Lowe","year":"2020","journal-title":"arXiv:1706.02275"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3064354"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1287\/trsc.2023.1199"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.trb.2018.07.010"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/j.trd.2021.102822"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2019.2948596"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.118941"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2021.103413"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.3002271"},{"key":"ref39","article-title":"Coupling user preference with external rewards to enable driver-centered and resource-aware EV charging recommendation","author":"Li","year":"2022","journal-title":"arXiv:2210.12693"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.3390\/en16248102"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/j.cie.2024.110711"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/EI250167.2020.9347221"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2024.3486342"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1016\/j.orl.2024.107107"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2023.3234176"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.126986"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2025.110055"},{"key":"ref48","article-title":"Safe offline reinforcement learning with feasibility-guided diffusion model","author":"Zheng","year":"2024","journal-title":"arXiv:2401. 10700"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.65109\/JSRC7365"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CDS49703.2020.00051"}],"container-title":["IEEE Transactions on Automation Science and Engineering"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/8856\/11323516\/11333289.pdf?arnumber=11333289","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,13]],"date-time":"2026-02-13T20:53:03Z","timestamp":1771015983000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11333289\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":50,"URL":"https:\/\/doi.org\/10.1109\/tase.2026.3651287","relation":{},"ISSN":["1545-5955","1558-3783"],"issn-type":[{"value":"1545-5955","type":"print"},{"value":"1558-3783","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}