{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T12:18:32Z","timestamp":1781871512152,"version":"3.54.5"},"reference-count":42,"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-nc-nd\/4.0\/"}],"funder":[{"name":"National Key R&D Program in China","award":["2019YFF0303102"],"award-info":[{"award-number":["2019YFF0303102"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61673232"],"award-info":[{"award-number":["61673232"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004147","name":"Tsinghua University Initiative Scientific Research Program","doi-asserted-by":"publisher","award":["2018Z05JDX005"],"award-info":[{"award-number":["2018Z05JDX005"]}],"id":[{"id":"10.13039\/501100004147","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004147","name":"Tsinghua University Initiative Scientific Research Program","doi-asserted-by":"publisher","award":["20183080016)"],"award-info":[{"award-number":["20183080016)"]}],"id":[{"id":"10.13039\/501100004147","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.2020.3034419","type":"journal-article","created":{"date-parts":[[2020,10,28]],"date-time":"2020-10-28T19:40:05Z","timestamp":1603914005000},"page":"199573-199585","source":"Crossref","is-referenced-by-count":31,"title":["Cooperative Control for Multi-Intersection Traffic Signal Based on Deep Reinforcement Learning and Imitation Learning"],"prefix":"10.1109","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4823-9710","authenticated-orcid":false,"given":"Yusen","family":"Huo","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9705-7748","authenticated-orcid":false,"given":"Qinghua","family":"Tao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianming","family":"Hu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","article-title":"Modeling purposeful adaptive behavior with the principle of maximum causal entropy","author":"ziebart","year":"2010"},{"key":"ref38","first-page":"22","article-title":"Constrained policy optimization","volume":"70","author":"achiam","year":"2017","journal-title":"Proc 34th Int Conf Mach Learn"},{"key":"ref33","article-title":"High-dimensional continuous control using generalized advantage estimation","author":"schulman","year":"2015","journal-title":"arXiv 1506 02438 [cs]"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1090\/S0002-9904-1954-09848-8"},{"key":"ref31","article-title":"Prisoner’s dilemma: A study in conflict and cooperation","author":"rapoport","year":"1965","journal-title":"Ann Arbor Paperbacks"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"key":"ref37","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"arXiv 1707 06347"},{"key":"ref36","first-page":"1889","article-title":"Trust region policy optimization","volume":"37","author":"schulman","year":"2015","journal-title":"Proc 32nd Int Conf Mach Learn"},{"key":"ref35","first-page":"267","article-title":"Approximately optimal approximate reinforcement learning","author":"kakade","year":"2002","journal-title":"Proc 19th Int Conf Mach Learn"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/203330.203343"},{"key":"ref10","article-title":"Deep reinforcement learning for traffic light control in vehicular networks","author":"liang","year":"2018","journal-title":"arXiv 1803 11115"},{"key":"ref40","article-title":"Soft actor-critic algorithms and applications","author":"haarnoja","year":"2018","journal-title":"arXiv 1812 05905"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-25808-9_4"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2018.8500414"},{"key":"ref13","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":"ref14","article-title":"Using a deep reinforcement learning agent for traffic signal control","author":"genders","year":"2016","journal-title":"arXiv 1611 01142"},{"key":"ref15","article-title":"Cooperative deep reinforcement learning for tra ic signal control","author":"liu","year":"2017","journal-title":"Proc ACM SIGKDD Conf Knowledge Discovery and Data Mining (KDD)"},{"key":"ref16","article-title":"Deep reinforcement learning for coordination in traffic light control","author":"van der pol","year":"2016"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5744"},{"key":"ref18","article-title":"Ig-rl: Inductive graph reinforcement learning for massive-scale traffic signal control","author":"devailly","year":"2020","journal-title":"arXiv 2003 05738"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2020.2976000"},{"key":"ref28","first-page":"627","article-title":"A reduction of imitation learning and structured prediction to no-regret online learning","author":"ross","year":"2011","journal-title":"Proc AISTATS"},{"key":"ref4","first-page":"1","article-title":"The 5G-enabled tactile Internet: Applications, requirements, and architecture","author":"simsek","year":"2016","journal-title":"Proc IEEE Wireless Commun Netw Conf"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICNN.1994.374604"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/GLOCOM.2012.6503418"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/MCOMSTD.2017.1700015"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-307-3.50012-5"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2013.2271951"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1061\/9780784481523.144"},{"key":"ref7","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.3390\/su7067784"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2013.2255286"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.enpol.2012.03.059"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1088\/1757-899X\/477\/1\/012052"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201311"},{"key":"ref21","article-title":"Efficient entropy for policy gradient with multidimensional action space","author":"zhang","year":"2018","journal-title":"Proc 4th Int Conf Learn Represent (ICLR) Workshop Track"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref24","article-title":"Deep deterministic policy gradient for urban traffic light control","author":"casas","year":"2017","journal-title":"arXiv 1703 09035"},{"key":"ref41","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","volume":"48","author":"mnih","year":"2016","journal-title":"Proc 33rd Int Conf Mach Learn"},{"key":"ref23","year":"2018","journal-title":"Openai five"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1038\/323533a0"},{"key":"ref25","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","author":"sutton","year":"1999","journal-title":"Proc 12th Int Conf Neural Inf Process Syst"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/8948470\/09241814.pdf?arnumber=9241814","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T15:57:49Z","timestamp":1642003069000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9241814\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/access.2020.3034419","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]}}}