{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T21:00:52Z","timestamp":1779397252372,"version":"3.53.1"},"reference-count":45,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2020,3,1]],"date-time":"2020-03-01T00:00:00Z","timestamp":1583020800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,3,1]],"date-time":"2020-03-01T00:00:00Z","timestamp":1583020800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,3,1]],"date-time":"2020-03-01T00:00:00Z","timestamp":1583020800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"French National Research Agency (ANR) Project","award":["ANR-11-LABX-0031-01"],"award-info":[{"award-number":["ANR-11-LABX-0031-01"]}]},{"name":"EURECOM partners: BMW Group; IABG; Monaco Telecom; Orange; SAP; ST Microelectronics; and Symantec"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Intell. Transport. Syst."],"published-print":{"date-parts":[[2020,3]]},"DOI":"10.1109\/tits.2019.2901791","type":"journal-article","created":{"date-parts":[[2019,3,15]],"date-time":"2019-03-15T23:22:33Z","timestamp":1552692153000},"page":"1086-1095","source":"Crossref","is-referenced-by-count":847,"title":["Multi-Agent Deep Reinforcement Learning for Large-Scale Traffic Signal Control"],"prefix":"10.1109","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9404-3348","authenticated-orcid":false,"given":"Tianshu","family":"Chu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1857-5569","authenticated-orcid":false,"given":"Jie","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lara","family":"Codeca","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0189-8719","authenticated-orcid":false,"given":"Zhaojian","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2014.12.009"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2013.2255286"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2018.04.008"},{"key":"ref32","author":"genders","year":"2016","journal-title":"Using a Deep Reinforcement Learning Agent for Traffic Signal Control [J]"},{"key":"ref31","author":"casas","year":"2017","journal-title":"Deep deterministic policy gradient for urban traffic light control"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2016.7799442"},{"key":"ref37","first-page":"1","article-title":"Coordinated deep reinforcement learners for traffic light control","volume":"16","author":"van der pol","year":"2016","journal-title":"Proc NIPS"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1080\/15472450.2017.1387546"},{"key":"ref35","first-page":"815","article-title":"Large-scale traffic grid signal control with regionalreinforcement learning","author":"chu","year":"2016","journal-title":"Proc Amer Control Conf"},{"key":"ref34","first-page":"1151","article-title":"Multi-agent reinforcement learning for traffic light control","author":"wiering","year":"2000","journal-title":"Proc 17th Int Conf Mach Learn (ICML)"},{"key":"ref10","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":"ref40","doi-asserted-by":"publisher","DOI":"10.23919\/ACC.2017.7963745"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4615-3618-5_2"},{"key":"ref13","first-page":"1008","article-title":"Actor-critic algorithms","volume":"13","author":"konda","year":"1999","journal-title":"Proc 12th Int Conf Neural Inf Process Syst"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2017.09.020"},{"key":"ref15","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"Int Conf Mach Learn"},{"key":"ref16","first-page":"227","article-title":"Coordinated reinforcement learning","author":"guestrin","year":"2002","journal-title":"Proc ICML"},{"key":"ref17","first-page":"1789","article-title":"Collaborative multiagent reinforcement learning by payoff propagation","volume":"7","author":"kok","year":"2006","journal-title":"J Mach Learn Res"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-307-3.50049-6"},{"key":"ref19","author":"foerster","year":"2017","journal-title":"Stabilising experience replay for deep multi-agent reinforcement learning"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2014.7039557"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/B978-0-08-029365-3.50048-1"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.2015.7172018"},{"key":"ref3","article-title":"Demand-responsive decentralized urban traffic control, Part I: Single intersection policies","author":"gartner","year":"1982"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/S0191-2615(03)00015-8"},{"key":"ref29","first-page":"1169","article-title":"Natural actor-critic for road traffic optimisation","author":"richter","year":"2007","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2010.2050688"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2017.07.003"},{"key":"ref2","first-page":"14","article-title":"Two traffic-responsive area traffic control methods: SCAT and SCOOT","volume":"25","author":"luk","year":"1984","journal-title":"Traffic Eng Control"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.2200\/S00268ED1V01Y201005AIM009"},{"key":"ref1","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":"ref20","doi-asserted-by":"publisher","DOI":"10.1512\/iumj.1957.6.56038"},{"key":"ref45","author":"wang","year":"2016","journal-title":"Sample efficient actor-critic with experience replay"},{"key":"ref22","first-page":"1523","article-title":"Multiagent planning with factored MDPs","volume":"1","author":"guestrin","year":"2001","journal-title":"Proc 14th Int Conf Neural Inform Process Syst Natural Synthetic"},{"key":"ref21","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","author":"sutton","year":"1999","journal-title":"Proc Adv Neural Inf Process Syst (NIPS)"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref24","article-title":"Intelligent traffic light control","author":"wiering","year":"2004"},{"key":"ref41","first-page":"128","article-title":"Recent development and applications of SUMO-simulation of urban mobility","volume":"5","author":"krajzewicz","year":"2012","journal-title":"International Journal on Advances in Systems and Measurements"},{"key":"ref23","first-page":"871","article-title":"Extending Q-learning to general adaptive multi-agent systems","author":"tesauro","year":"2004","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref44","first-page":"14","article-title":"Monaco SUMO traffic (MoST) scenario: A 3D mobility scenario for cooperative ITS","author":"codeca","year":"2018","journal-title":"Proc SUMO User Conf Simulating Auton Intermodal Transp Syst"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2010.2091408"},{"key":"ref43","author":"saxe","year":"2013","journal-title":"Exact solutions to the nonlinear dynamics of learning in deep linear neural networks"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2009.04.005"}],"container-title":["IEEE Transactions on Intelligent Transportation Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6979\/9018398\/08667868.pdf?arnumber=8667868","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T16:02:41Z","timestamp":1651075361000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8667868\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,3]]},"references-count":45,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tits.2019.2901791","relation":{},"ISSN":["1524-9050","1558-0016"],"issn-type":[{"value":"1524-9050","type":"print"},{"value":"1558-0016","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,3]]}}}