{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T14:30:30Z","timestamp":1773066630933,"version":"3.50.1"},"reference-count":26,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Basic Research Program of China","doi-asserted-by":"publisher","award":["2018YFE0205503"],"award-info":[{"award-number":["2018YFE0205503"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2020]]},"DOI":"10.1109\/access.2020.3014076","type":"journal-article","created":{"date-parts":[[2020,8,4]],"date-time":"2020-08-04T21:15:49Z","timestamp":1596575749000},"page":"143333-143341","source":"Crossref","is-referenced-by-count":21,"title":["Dynamic Fleet Management With Rewriting Deep Reinforcement Learning"],"prefix":"10.1109","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4482-6715","authenticated-orcid":false,"given":"Wenqi","family":"Zhang","sequence":"first","affiliation":[{"name":"National Engineering Laboratory for Mobile Network Technologies, Beijing University of Posts and Telecommunications, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9392-475X","authenticated-orcid":false,"given":"Qiang","family":"Wang","sequence":"additional","affiliation":[{"name":"National Engineering Laboratory for Mobile Network Technologies, Beijing University of Posts and Telecommunications, Beijing, China"}]},{"given":"Jingjing","family":"Li","sequence":"additional","affiliation":[{"name":"National Engineering Laboratory for Mobile Network Technologies, Beijing University of Posts and Telecommunications, Beijing, China"}]},{"given":"Chen","family":"Xu","sequence":"additional","affiliation":[{"name":"National Engineering Laboratory for Mobile Network Technologies, Beijing University of Posts and Telecommunications, Beijing, China"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/MITS.2019.2962159"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2019.2909109"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2018.8485988"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2019.2931830"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219824"},{"key":"ref15","first-page":"1995","article-title":"Dueling network architectures for deep reinforcement learning","author":"wang","year":"2016","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref16","volume":"1","author":"sutton","year":"1998","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2017.05.431"},{"key":"ref18","article-title":"An overview of gradient descent optimization algorithms","author":"ruder","year":"2016","journal-title":"arXiv 1609 04747"},{"key":"ref19","first-page":"1","article-title":"Convergence of Q-learning: A simple proof","author":"melo","year":"2001"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TIA.2019.2926359"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2017.2740438"},{"key":"ref6","first-page":"9839","article-title":"Reinforcement learning for solving the vehicle routing problem","author":"nazari","year":"2018","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2018.2872442"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3357978"},{"key":"ref7","article-title":"Neural combinatorial optimization with reinforcement learning","author":"bello","year":"2016","journal-title":"arXiv 1611 09940"},{"key":"ref2","year":"0"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2019.00129"},{"key":"ref1","year":"0"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1994.6.6.1185"},{"key":"ref22","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2018.2890726"},{"key":"ref24","article-title":"Dynamic vehicle dispatching based on minimum fleet a deep reinforcement learning method","author":"zhang","year":"2019","journal-title":"Proc Neural Inf Process Syst (NeurIPS Deep Reinforcement Learn Workshop)"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2009.2028577"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4842-2766-4_8"},{"key":"ref25","author":"goodfellow","year":"2016","journal-title":"Deep Learning"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/8948470\/09157835.pdf?arnumber=9157835","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,8]],"date-time":"2022-09-08T19:45:23Z","timestamp":1662666323000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9157835\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/access.2020.3014076","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]}}}