{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,9]],"date-time":"2026-05-09T16:56:54Z","timestamp":1778345814031,"version":"3.51.4"},"reference-count":32,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2021,8,1]],"date-time":"2021-08-01T00:00:00Z","timestamp":1627776000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,8,1]],"date-time":"2021-08-01T00:00:00Z","timestamp":1627776000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,8,1]],"date-time":"2021-08-01T00:00:00Z","timestamp":1627776000000},"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":["61906027"],"award-info":[{"award-number":["61906027"]}],"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":["61906135"],"award-info":[{"award-number":["61906135"]}],"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":["61803295"],"award-info":[{"award-number":["61803295"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2019M661080"],"award-info":[{"award-number":["2019M661080"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100007128","name":"Natural Science Foundation of Shaanxi Province","doi-asserted-by":"publisher","award":["2020JQ-070"],"award-info":[{"award-number":["2020JQ-070"]}],"id":[{"id":"10.13039\/501100007128","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Veh. Technol."],"published-print":{"date-parts":[[2021,8]]},"DOI":"10.1109\/tvt.2021.3090796","type":"journal-article","created":{"date-parts":[[2021,6,22]],"date-time":"2021-06-22T20:01:36Z","timestamp":1624392096000},"page":"7426-7436","source":"Crossref","is-referenced-by-count":39,"title":["Independent Reinforcement Learning for Weakly Cooperative Multiagent Traffic Control Problem"],"prefix":"10.1109","volume":"70","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9157-6050","authenticated-orcid":false,"given":"Chengwei","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shan","family":"Jin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6031-9334","authenticated-orcid":false,"given":"Wanli","family":"Xue","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaofei","family":"Xie","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6705-3831","authenticated-orcid":false,"given":"Shengyong","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rong","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3308558.3314139"},{"key":"ref31","first-page":"487","article-title":"Multi-agent reinforcement learning: Independent vs. cooperative agents","author":"tan","year":"1997"},{"key":"ref30","first-page":"4292","article-title":"Qmix: Monotonic value function factorisation for deep multi-agent reinforcement learning","author":"rashid","year":"2018","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1017\/S0269888912000057"},{"key":"ref11","article-title":"Value-decomposition networks for cooperative multi-agent learning","author":"sunehag","year":"2017"},{"key":"ref12","first-page":"6379","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","author":"lowe","year":"2017"},{"key":"ref13","first-page":"5887","article-title":"Qtran: Learning to factorize with transformation for cooperative multi-agent reinforcement learning","author":"son","year":"2019"},{"key":"ref14","first-page":"2914","article-title":"Lenient learning in independent-learner stochastic cooperative games","volume":"17","author":"wei","year":"2016","journal-title":"J Mach Learn Res"},{"key":"ref15","first-page":"2681","article-title":"Deep decentralized multi-task multi-agent reinforcement learning under partial observability","volume":"70","author":"omidshafiei","year":"2017","journal-title":"Proc 34th Int Conf Mach Learn"},{"key":"ref16","first-page":"443","article-title":"Lenient multi-agent deep reinforcement learning","author":"palmer","year":"2018"},{"key":"ref17","first-page":"1315","article-title":"Independent generative adversarial self-imitation learning in cooperative multiagent systems","author":"hao","year":"2019","journal-title":"Proc 18th Int Conf Auton Agents MultiAgent Syst"},{"key":"ref18","first-page":"43","article-title":"Negative update intervals in deep multi-agent reinforcement learning","author":"palmer","year":"2019","journal-title":"Proc 18th Int Conf Auton Agents MultiAgent Syst"},{"key":"ref19","first-page":"2094","article-title":"Deep reinforcement learning with double q-learning","author":"van hasselt","year":"2016"},{"key":"ref28","article-title":"Diagnosing reinforcement learning for traffic signal control","author":"zheng","year":"2019"},{"key":"ref4","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":"ref27","first-page":"746","article-title":"The dynamics of reinforcement learning in cooperative multiagent systems","author":"claus","year":"1998"},{"key":"ref3","first-page":"45","author":"cools","year":"2013","journal-title":"Self-organizing traffic lights A realistic simulation"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2018.8569301"},{"key":"ref29","article-title":"Multi-agent reinforcement learning for networked system control","author":"chu","year":"2019","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref5","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":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2014.12.009"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3357902"},{"key":"ref2","first-page":"212","article-title":"Multiband-a variable-bandwidth arterial progression scheme","author":"gartner","year":"1990","journal-title":"Transp Res Rec"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1613\/jair.4818"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2018.2890726"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2019.2901791"},{"key":"ref22","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":"ref21","article-title":"Intelligent traffic light control","author":"wiering","year":"2004","journal-title":"Institute of Information and Computing Sciences Utrecht University"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/APCC.2018.8633520"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1017\/S0269888912000057"},{"key":"ref25","first-page":"1995","article-title":"Dueling network architectures for deep reinforcement learning","author":"wang","year":"2016","journal-title":"Proc Int Conf Mach Learn"}],"container-title":["IEEE Transactions on Vehicular Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/25\/9514482\/09462486.pdf?arnumber=9462486","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:48:37Z","timestamp":1652194117000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9462486\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,8]]},"references-count":32,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tvt.2021.3090796","relation":{},"ISSN":["0018-9545","1939-9359"],"issn-type":[{"value":"0018-9545","type":"print"},{"value":"1939-9359","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,8]]}}}