{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,16]],"date-time":"2026-05-16T03:56:34Z","timestamp":1778903794187,"version":"3.51.4"},"reference-count":51,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2020,6,1]],"date-time":"2020-06-01T00:00:00Z","timestamp":1590969600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,6,1]],"date-time":"2020-06-01T00:00:00Z","timestamp":1590969600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,6,1]],"date-time":"2020-06-01T00:00:00Z","timestamp":1590969600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Stanford Center for Sustainable Development and Global Competitiveness"},{"DOI":"10.13039\/501100009592","name":"Project of Beijing Municipal Science and Technology Commission","doi-asserted-by":"publisher","award":["Z181100003118014"],"award-info":[{"award-number":["Z181100003118014"]}],"id":[{"id":"10.13039\/501100009592","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"Project of NSFC","doi-asserted-by":"publisher","award":["61327902"],"award-info":[{"award-number":["61327902"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Cybern."],"published-print":{"date-parts":[[2020,6]]},"DOI":"10.1109\/tcyb.2019.2904742","type":"journal-article","created":{"date-parts":[[2019,3,29]],"date-time":"2019-03-29T18:53:13Z","timestamp":1553885593000},"page":"2687-2700","source":"Crossref","is-referenced-by-count":194,"title":["Cooperative Deep Reinforcement Learning for Large-Scale Traffic Grid Signal Control"],"prefix":"10.1109","volume":"50","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9173-2984","authenticated-orcid":false,"given":"Tian","family":"Tan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5721-9551","authenticated-orcid":false,"given":"Feng","family":"Bao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2871-8922","authenticated-orcid":false,"given":"Yue","family":"Deng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alex","family":"Jin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7043-3061","authenticated-orcid":false,"given":"Qionghai","family":"Dai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1857-5569","authenticated-orcid":false,"given":"Jie","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","article-title":"Prioritized experience replay","author":"schaul","year":"2016","journal-title":"Proc ICLR"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2016.11.041"},{"key":"ref33","author":"casas","year":"2017","journal-title":"Deep deterministic policy gradient for urban traffic light control"},{"key":"ref32","first-page":"1","article-title":"Using the max-plus algorithm for multiagent decision making in coordination graphs","author":"kok","year":"2005","journal-title":"Robot Soccer World Cup"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2010.5596468"},{"key":"ref30","article-title":"Using a deep reinforcement learning agent for traffic signal control","volume":"abs 1611 1142","author":"genders","year":"2016","journal-title":"CoRR"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2017.2707520"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2018.2810117"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2016.2611613"},{"key":"ref34","first-page":"187a","article-title":"Continuous control with deep reinforcement learning","volume":"8","author":"lillicrap","year":"2015","journal-title":"Comput Sci"},{"key":"ref28","doi-asserted-by":"crossref","first-page":"247","DOI":"10.1109\/JAS.2016.7508798","article-title":"Traffic signal timing via deep reinforcement learning","volume":"3","author":"li","year":"2016","journal-title":"IEEE\/CAA Journal of Automatica Sinica"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1049\/iet-its.2009.0070"},{"key":"ref29","first-page":"1","article-title":"Coordinated deep reinforcement learners for traffic light control","author":"van der pol","year":"2016","journal-title":"Proc NIPS"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.7249\/RM3420"},{"key":"ref1","author":"burfeind","year":"2017","journal-title":"Los angeles tops inrix global congestion ranking"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"ref22","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2014.09.003"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/MCI.2010.938363"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2522401"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICEC.1994.350012"},{"key":"ref25","volume":"1","author":"sutton","year":"1998","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2009.02.003"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.3141\/2257-10"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/S0377-2217(00)00123-5"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICNC.2009.653"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178838"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2011.04.011"},{"key":"ref13","article-title":"Intelligent traffic light control","author":"wiering","year":"2004"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2014.01.007"},{"key":"ref15","first-page":"1101","article-title":"Coordinating multi-agent reinforcement learning with limited communication","author":"zhang","year":"2013","journal-title":"Proc Int Conf Auton Agents and Multi Agent Syst"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.2016.7525014"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref18","first-page":"652","article-title":"Large-scale traffic grid signal control using decentralized fuzzy reinforcement learning","author":"tan","year":"2016","journal-title":"Proc SAI Intell Syst Conf"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2013.2255286"},{"key":"ref4","article-title":"Traffic signal settings","author":"webster","year":"1958"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2011.2161577"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1088\/1742-5468\/2008\/04\/P04019"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1057\/jors.1963.61"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCA.2010.2052606"},{"key":"ref7","first-page":"29","article-title":"Self-organizing traffic lights","volume":"16","author":"gershenson","year":"2005","journal-title":"Complex Syst"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2016.7795752"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2010.2050688"},{"key":"ref46","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":"ref45","first-page":"1","article-title":"Sumo—Simulation of urban mobility: An overview","author":"behrisch","year":"2011","journal-title":"Proc Int Conf Adv Syst Simulation (SIMUL)"},{"key":"ref48","first-page":"315","article-title":"Deep sparse rectifier neural networks","author":"glorot","year":"2011","journal-title":"Proc 14th Int Conf Artificial Intell"},{"key":"ref47","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"arXiv preprint arXiv 1412 6980"},{"key":"ref42","article-title":"Deep reinforcement learning in large discrete action spaces","author":"dulac-arnold","year":"2015","journal-title":"arXiv preprint arXiv 1512 00327"},{"key":"ref41","doi-asserted-by":"crossref","first-page":"331","DOI":"10.1016\/S0927-0507(05)80172-0","article-title":"Markov decision processes","volume":"2","author":"puterman","year":"1990","journal-title":"Handbooks in Operations Research and Management Science"},{"key":"ref44","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-642-27645-3","article-title":"Reinforcement learning","volume":"12","author":"wiering","year":"2012","journal-title":"Adaptation Learning and Optimization"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/T-C.1975.224297"}],"container-title":["IEEE Transactions on Cybernetics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6221036\/9089323\/08676356.pdf?arnumber=8676356","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T17:20:59Z","timestamp":1651080059000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8676356\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,6]]},"references-count":51,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tcyb.2019.2904742","relation":{},"ISSN":["2168-2267","2168-2275"],"issn-type":[{"value":"2168-2267","type":"print"},{"value":"2168-2275","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,6]]}}}