{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T15:30:59Z","timestamp":1775835059408,"version":"3.50.1"},"reference-count":45,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2020,8,1]],"date-time":"2020-08-01T00:00:00Z","timestamp":1596240000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,8,1]],"date-time":"2020-08-01T00:00:00Z","timestamp":1596240000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,8,1]],"date-time":"2020-08-01T00:00:00Z","timestamp":1596240000000},"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":["61972448"],"award-info":[{"award-number":["61972448"]}],"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":["61872150"],"award-info":[{"award-number":["61872150"]}],"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":["61872049"],"award-info":[{"award-number":["61872049"]}],"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":["61902445"],"award-info":[{"award-number":["61902445"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Guangdong Basic and Applied Basic Research Foundation","award":["2020A1515011209"],"award-info":[{"award-number":["2020A1515011209"]}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["19lgpy222"],"award-info":[{"award-number":["19lgpy222"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003453","name":"Natural Science Foundation of Guangdong Province","doi-asserted-by":"publisher","award":["2019A1515011798"],"award-info":[{"award-number":["2019A1515011798"]}],"id":[{"id":"10.13039\/501100003453","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Veh. Technol."],"published-print":{"date-parts":[[2020,8]]},"DOI":"10.1109\/tvt.2020.2997896","type":"journal-article","created":{"date-parts":[[2020,5,28]],"date-time":"2020-05-28T20:35:51Z","timestamp":1590698151000},"page":"8243-8256","source":"Crossref","is-referenced-by-count":263,"title":["Multi-Agent Deep Reinforcement Learning for Urban Traffic Light Control in Vehicular Networks"],"prefix":"10.1109","volume":"69","author":[{"given":"Tong","family":"Wu","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8629-4622","authenticated-orcid":false,"given":"Pan","family":"Zhou","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5865-7724","authenticated-orcid":false,"given":"Kai","family":"Liu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9258-9929","authenticated-orcid":false,"given":"Yali","family":"Yuan","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3772-290X","authenticated-orcid":false,"given":"Xiumin","family":"Wang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7035-6446","authenticated-orcid":false,"given":"Huawei","family":"Huang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1755-0183","authenticated-orcid":false,"given":"Dapeng Oliver","family":"Wu","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","first-page":"29","article-title":"Deep recurrent q-learning for partially observable mdps","author":"hausknecht","year":"0","journal-title":"Proc AAAI Fall Symp Series"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.429"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2018.8500414"},{"key":"ref32","article-title":"Using a deep reinforcement learning agent for traffic signal control","author":"genders","year":"2016","journal-title":"arXiv 1611 01142"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2010.2091408"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220096"},{"key":"ref37","first-page":"1151","article-title":"Multi-agent reinforcement learning for traffic light control","author":"wiering","year":"0","journal-title":"Proc Mach Learn Proc 17th Int Conf"},{"key":"ref36","article-title":"Deep reinforcement learning for intelligent transportation systems","author":"liu","year":"2018"},{"key":"ref35","article-title":"Distributed traffic light control at uncoupled intersections with real-world topology by deep reinforcement learning","author":"schutera","year":"2018","journal-title":"2018 NIPS MLITS Workshop"},{"key":"ref34","article-title":"Coordinated deep reinforcement learners for traffic light control","author":"pol","year":"0","journal-title":"Proc Learn Inference Control Multi-Agent Syst"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1287\/trsc.31.1.5"},{"key":"ref40","article-title":"Memory-based control with recurrent neural networks","author":"heess","year":"2015","journal-title":"arXiv 1512 04455"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/S0377-2217(00)00123-5"},{"key":"ref12","doi-asserted-by":"crossref","first-page":"261","DOI":"10.1109\/TITS.2006.874716","article-title":"Neural networks for real-time traffic signal control","volume":"7","author":"choy","year":"2006","journal-title":"IEEE Trans Intell Transp Syst"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2009.2034383"},{"key":"ref14","first-page":"105","article-title":"A survey of intelligence methods in urban traffic signal control","volume":"7","author":"liu","year":"2007","journal-title":"IJCSNS Int J Comput Sci Netw Secur"},{"key":"ref15","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref16","author":"puterman","year":"2014","journal-title":"Markov Decision Processes Discrete Stochastic Dynamic Programming"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2743240"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref19","first-page":"6379","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","author":"lowe","year":"0","journal-title":"Proc Advances Neural Inf Process Syst"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2017.8317730"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2008.4539481"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2015.2444095"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2017.2702388"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2018.2890726"},{"key":"ref8","first-page":"67","article-title":"The sydney cooridinated adaptive traffic (SCAT) system-principles, methodology, algorithm","author":"lowrie","year":"0","journal-title":"Proc Int Conf Road Traffic Signaling"},{"key":"ref7","first-page":"190","article-title":"The scoot on-line traffic signal optimisation technique","volume":"23","author":"hunt","year":"1982","journal-title":"Traffic Eng Control"},{"key":"ref2","article-title":"Traffic signal settings","author":"webster","year":"1958"},{"key":"ref9","article-title":"OPAC: A demand-responsive strategy for traffic signal","author":"gartner","year":"0"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cstp.2014.03.001"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0172395"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-335-6.50027-1"},{"key":"ref22","first-page":"5571","article-title":"Mean field multi-agent reinforcement learning","author":"yang","year":"0","journal-title":"Proc Int Conf Machine Learning (ICML)"},{"key":"ref21","article-title":"Cooperation and communication in multiagent deep reinforcement learning","author":"hausknecht","year":"2016"},{"key":"ref42","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"arXiv 1412 6980"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2013.2255286"},{"key":"ref41","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2015","journal-title":"arXiv 1509 02971"},{"key":"ref23","article-title":"Deep deterministic policy gradient for urban traffic light control","author":"casas","year":"2017","journal-title":"arXiv 1703 09035"},{"key":"ref44","first-page":"45","article-title":"Self-organizing traffic lights: A realistic simulation","author":"cools","year":"0","journal-title":"Proc Advances Appl Self-Organizing Syst"},{"key":"ref26","first-page":"1","article-title":"Cooperative deep reinforcement learning for traffic signal control","author":"liu","year":"0","journal-title":"Proc 6th Int Workshop Urban Comput (UrbComp)"},{"key":"ref43","first-page":"183","article-title":"Sumo (simulation of urban mobility)-an open-source traffic simulation","author":"krajzewicz","year":"0","journal-title":"Proc 4th Middle East Symp Simulation Modeling"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2014.6958095"}],"container-title":["IEEE Transactions on Vehicular Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/25\/9166810\/09103316.pdf?arnumber=9103316","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T13:45:27Z","timestamp":1651067127000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9103316\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,8]]},"references-count":45,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tvt.2020.2997896","relation":{},"ISSN":["0018-9545","1939-9359"],"issn-type":[{"value":"0018-9545","type":"print"},{"value":"1939-9359","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,8]]}}}