{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,24]],"date-time":"2026-07-24T04:02:45Z","timestamp":1784865765891,"version":"3.55.0"},"reference-count":50,"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\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["2019JBM040"],"award-info":[{"award-number":["2019JBM040"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["71971017"],"award-info":[{"award-number":["71971017"]}],"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":["91746201"],"award-info":[{"award-number":["91746201"]}],"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":["71621001"],"award-info":[{"award-number":["71621001"]}],"id":[{"id":"10.13039\/501100001809","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.2020.2974885","type":"journal-article","created":{"date-parts":[[2020,2,18]],"date-time":"2020-02-18T21:33:43Z","timestamp":1582061623000},"page":"37087-37104","source":"Crossref","is-referenced-by-count":15,"title":["A Deep Adaptive Traffic Signal Controller With Long-Term Planning Horizon and Spatial-Temporal State Definition Under Dynamic Traffic Fluctuations"],"prefix":"10.1109","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6719-8969","authenticated-orcid":false,"given":"Shurong","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6703-3419","authenticated-orcid":false,"given":"Chong","family":"Wei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0120-9183","authenticated-orcid":false,"given":"Xuedong","family":"Yan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4492-6636","authenticated-orcid":false,"given":"Lu","family":"Ma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Deqi","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8596-5308","authenticated-orcid":false,"given":"Ying","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/VNIS.1989.98779"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2009.04.005"},{"key":"ref33","volume":"109","author":"kyamakya","year":"2017","journal-title":"Recent Advances in Nonlinear Dynamics and Synchronization With Selected Applications in Electrical Engineering Neurocomputing and Transportation"},{"key":"ref32","first-page":"40","article-title":"MAXBAND: A versatile program for setting signals on arteries and triangular networks","author":"little","year":"1981","journal-title":"Transp Res Rec"},{"key":"ref31","author":"husch","year":"2003","journal-title":"Synchro 6 Traffic Signal Software User Guide"},{"key":"ref30","first-page":"181","article-title":"‘TRANSYT’ method for area traffic control","volume":"10","author":"robertson","year":"1969","journal-title":"Traffic Eng Control"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/S0968-090X(96)00009-5"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2013.6728480"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TCST.2016.2634459"},{"key":"ref34","first-page":"385","article-title":"Self-optimising traffic signal control using microprocessors. The TRRL MOVA strategy for isolated intersections","volume":"27","author":"vincent","year":"1986","journal-title":"Traffic Eng Control"},{"key":"ref28","first-page":"1475","article-title":"Reinforcement learning with long short-term memory","author":"bakker","year":"2002","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/s10772-018-09573-7"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.trb.2008.03.005"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2009.11.009"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2003.819606"},{"key":"ref20","doi-asserted-by":"crossref","first-page":"484","DOI":"10.1038\/nature16961","article-title":"Mastering the game of go with deep neural networks and tree search","volume":"529","author":"silver","year":"2016","journal-title":"Nature"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2018.12.007"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913495721"},{"key":"ref24","first-page":"1169","article-title":"Natural actor-critic for road traffic optimisation","volume":"19","author":"richter","year":"2007","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2017.09.004"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2017.10.016"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2018.12.004"},{"key":"ref50","author":"glick","year":"2015","journal-title":"Reinforcement Learning For Adaptive Traffic Signal Control"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1287\/trsc.35.2.148.10136"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/S0965-8564(98)00049-4"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.3141\/1811-18"},{"key":"ref12","article-title":"SCOOT-a traffic responsive method of coordinating signals","author":"hunt","year":"1014"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/T-VT.1980.23833"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1287\/trsc.31.1.5"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2015.01.007"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1155\/2010\/724035"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1613\/jair.301"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(99)00052-1"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.compchemeng.2017.10.008"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2011.2161577"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2014.09.003"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-25808-9_4"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3068287"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2009.06.003"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2017.09.020"},{"key":"ref49","first-page":"265","article-title":"TensorFlow: A system for large-scale machine learning","volume":"16","author":"abadi","year":"2016","journal-title":"Proc OSDI"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/S0965-8564(00)00014-8"},{"key":"ref46","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"arXiv 1707 06347"},{"key":"ref45","first-page":"29","article-title":"An actor-critic algorithm for learning rate learning","volume":"3","author":"lundgren","year":"1976","journal-title":"International Journal of Signal and Image Processing"},{"key":"ref48","first-page":"128","article-title":"Recent development and applications of SUMO-simulation of urban mobility","volume":"5","author":"krajzewicz","year":"2012","journal-title":"Int J Adv Syst Meas"},{"key":"ref47","first-page":"267","article-title":"Approximately optimal approximate reinforcement learning","volume":"2","author":"kakade","year":"2002","journal-title":"Proc ICML"},{"key":"ref42","first-page":"1151","article-title":"Multi-agent reinforcement learning for traffic light control","author":"wiering","year":"2000","journal-title":"Proc Int Conf Machine Learn (ICML)"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/S0968-090X(00)00047-4"},{"key":"ref44","first-page":"1","article-title":"A critical review of recurrent neural networks for sequence learning","author":"lipton","year":"2015","journal-title":"arXiv 1506 00019"},{"key":"ref43","first-page":"1","article-title":"Coordinated deep reinforcement learners for traffic light control","author":"van der pol","year":"2016","journal-title":"Proc NIPS Workshop Learn Inference Control Multi-Agent Syst"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/8948470\/09001092.pdf?arnumber=9001092","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,12,17]],"date-time":"2021-12-17T19:51:44Z","timestamp":1639770704000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9001092\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":50,"URL":"https:\/\/doi.org\/10.1109\/access.2020.2974885","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]}}}