{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T15:23:23Z","timestamp":1783610603140,"version":"3.55.0"},"reference-count":60,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2022,9,1]],"date-time":"2022-09-01T00:00:00Z","timestamp":1661990400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,9,1]],"date-time":"2022-09-01T00:00:00Z","timestamp":1661990400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,9,1]],"date-time":"2022-09-01T00:00:00Z","timestamp":1661990400000},"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","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002920","name":"Research Grants Council of the Hong Kong Special Administrative Region","doi-asserted-by":"publisher","award":["PolyU 152101\/17E"],"award-info":[{"award-number":["PolyU 152101\/17E"]}],"id":[{"id":"10.13039\/501100002920","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002920","name":"Research Grants Council of the Hong Kong Special Administrative Region","doi-asserted-by":"publisher","award":["R5029-18"],"award-info":[{"award-number":["R5029-18"]}],"id":[{"id":"10.13039\/501100002920","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2022,9]]},"DOI":"10.1109\/tnnls.2021.3060187","type":"journal-article","created":{"date-parts":[[2021,3,2]],"date-time":"2021-03-02T20:43:52Z","timestamp":1614717832000},"page":"4742-4756","source":"Crossref","is-referenced-by-count":64,"title":["An Integrated Reinforcement Learning and Centralized Programming Approach for Online Taxi Dispatching"],"prefix":"10.1109","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0283-0676","authenticated-orcid":false,"given":"Enming","family":"Liang","sequence":"first","affiliation":[{"name":"Guangdong Key Laboratory of Intelligent Transportation Systems, School of Intelligent Systems Engineering, Sun Yat-sen University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kexin","family":"Wen","sequence":"additional","affiliation":[{"name":"Guangdong Key Laboratory of Intelligent Transportation Systems, School of Intelligent Systems Engineering, Sun Yat-sen University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7625-3712","authenticated-orcid":false,"given":"William H. K.","family":"Lam","sequence":"additional","affiliation":[{"name":"Department of Civil and Environmental Engineering, The Hong Kong Polytechnic University, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6648-1255","authenticated-orcid":false,"given":"Agachai","family":"Sumalee","sequence":"additional","affiliation":[{"name":"School of Integrated Innovation, Chulalongkorn University, Bangkok, Thailand"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1559-7287","authenticated-orcid":false,"given":"Renxin","family":"Zhong","sequence":"additional","affiliation":[{"name":"Guangdong Key Laboratory of Intelligent Transportation Systems, School of Intelligent Systems Engineering, Sun Yat-sen University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219824"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330724"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2018.00077"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2020.3006084"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3308558.3313433"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3357799"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2019.00133"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219993"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2018.8485988"},{"key":"ref10","first-page":"8102","article-title":"Credit assignment for collective multiagent RL with global rewards","volume-title":"Proc. NIPS","author":"Nguyen"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2018.2875524"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.trb.2018.12.013"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2019.12.005"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1287\/trsc.2017.0767"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejor.2020.01.033"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.trb.2019.01.017"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2019.00129"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3357978"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-77778-8"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487272"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2016.2529580"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1287\/opre.2018.1763"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2018.2882861"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1126\/science.153.3731.34"},{"key":"ref25","volume-title":"Markov Decision Processes: Discrete Stochastic Dynamic Programming","author":"Puterman","year":"2014"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1002\/SERIES1345"},{"key":"ref27","first-page":"1040","article-title":"Learning from demonstration","volume-title":"Proc. NIPS","author":"Schaal"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/s1364-6613(99)01327-3"},{"key":"ref29","first-page":"2","article-title":"Algorithms for inverse reinforcement learning","volume-title":"Proc. ICML","volume":"1","author":"Ng"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3022950"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2885374"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2945019"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2977924"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2801880"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2885530"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2955857"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2927531"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1006\/juec.1996.0035"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3033274.3085098"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1287\/opre.2018.1800"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/j.trb.2019.02.011"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1016\/j.trb.2019.11.005"},{"key":"ref45","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton","year":"2018"},{"issue":"54","key":"ref46","first-page":"1","article-title":"Deep reinforcement learning for swarm systems","volume":"20","author":"H\u00fcttenrauch","year":"2019","journal-title":"J. Mach. Learn. Res."},{"key":"ref47","first-page":"2085","article-title":"Value-decomposition networks for cooperative multi-agent learning based on team reward","volume-title":"Proc. AAMAS","author":"Sunehag"},{"key":"ref48","first-page":"4295","article-title":"Qmix: Monotonic value function factorisation for deep multi-agent reinforcement learning","volume-title":"Proc. ICML","author":"Rashid"},{"key":"ref49","first-page":"2137","article-title":"Learning to communicate with deep multi-agent reinforcement learning","volume-title":"Proc. NIPS","author":"Foerster"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11794"},{"key":"ref51","first-page":"5887","article-title":"QTRAN: Learning to factorize with transformation for cooperative multi-agent reinforcement learning","volume-title":"Proc. ICML","author":"Son"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-68279-0_2"},{"key":"ref53","first-page":"1","article-title":"Prioritized experience replay","volume-title":"Proc. ICLR","author":"Schaul"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/LCSYS.2020.3004423"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2013.2276571"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2010.5717148"},{"key":"ref57","first-page":"4026","article-title":"Deep exploration via bootstrapped DQN","volume-title":"Proc. NIPS","author":"Osband"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1016\/j.compenvurbsys.2017.05.004"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1038\/Nature14539"},{"key":"ref60","first-page":"5571","article-title":"Mean field multi-agent reinforcement learning","volume-title":"Proc. ICML","author":"Yang"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/9872163\/09366995.pdf?arnumber=9366995","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,9]],"date-time":"2024-01-09T23:42:09Z","timestamp":1704843729000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9366995\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,9]]},"references-count":60,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2021.3060187","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,9]]}}}