{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T09:11:10Z","timestamp":1777367470550,"version":"3.51.4"},"reference-count":56,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2022,8,1]],"date-time":"2022-08-01T00:00:00Z","timestamp":1659312000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,8,1]],"date-time":"2022-08-01T00:00:00Z","timestamp":1659312000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,8,1]],"date-time":"2022-08-01T00:00:00Z","timestamp":1659312000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2018YFB1600600"],"award-info":[{"award-number":["2018YFB1600600"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61976034"],"award-info":[{"award-number":["61976034"]}],"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":["61572104"],"award-info":[{"award-number":["61572104"]}],"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":["U1808206"],"award-info":[{"award-number":["U1808206"]}],"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":["the"],"award-info":[{"award-number":["the"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100017683","name":"Dalian Science and Technology Innovation Fund","doi-asserted-by":"publisher","award":["2019J12GX035"],"award-info":[{"award-number":["2019J12GX035"]}],"id":[{"id":"10.13039\/501100017683","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Intell. Transport. Syst."],"published-print":{"date-parts":[[2022,8]]},"DOI":"10.1109\/tits.2021.3115240","type":"journal-article","created":{"date-parts":[[2021,10,2]],"date-time":"2021-10-02T01:56:30Z","timestamp":1633139790000},"page":"12572-12587","source":"Crossref","is-referenced-by-count":60,"title":["Multi-Agent Transfer Reinforcement Learning With Multi-View Encoder for Adaptive Traffic Signal Control"],"prefix":"10.1109","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8937-1515","authenticated-orcid":false,"given":"Hongwei","family":"Ge","sequence":"first","affiliation":[{"name":"College of Computer Science and Technology, Dalian University of Technology, Dalian, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3131-2149","authenticated-orcid":false,"given":"Dongwan","family":"Gao","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Dalian University of Technology, Dalian, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2794-8654","authenticated-orcid":false,"given":"Liang","family":"Sun","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Dalian University of Technology, Dalian, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9929-2650","authenticated-orcid":false,"given":"Yaqing","family":"Hou","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Dalian University of Technology, Dalian, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4371-3663","authenticated-orcid":false,"given":"Chao","family":"Yu","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Sun Yat-sen University, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5133-3978","authenticated-orcid":false,"given":"Yuxin","family":"Wang","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Dalian University of Technology, Dalian, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7224-5694","authenticated-orcid":false,"given":"Guozhen","family":"Tan","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Dalian University of Technology, Dalian, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.2984033"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2016.2613740"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1287\/trsc.6.3.260"},{"issue":"4","key":"ref4","first-page":"190","article-title":"The SCOOT on-line traffic signal optimisation technique","volume":"23","author":"Hunt","year":"1982","journal-title":"Traffic Eng. Control"},{"issue":"1","key":"ref5","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":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/S0191-2615(03)00015-8"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CIMSiM.2010.95"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.24200\/sci.2017.4442"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-85563-7_8"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2008.2005842"},{"issue":"3","key":"ref11","first-page":"2911","article-title":"Research on traffic signal control algorithm based on self-organizing competitive neural network and optimization model","volume":"28","author":"Wan","year":"2017","journal-title":"Agro Food Ind. Hi-Tech"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2010.2050688"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2012.6338691"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s40815-016-0143-7"},{"key":"ref15","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton","year":"2018"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1061\/(asce)0733-947x(2003)129:3(278)"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2010.2091408"},{"key":"ref18","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Haarnoja"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/SMC.2013.617"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.trpro.2015.09.070"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2017.05.327"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2019.2901791"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1049\/iet-its.2018.5170"},{"key":"ref24","article-title":"Comprehensive analysis of reinforcement learning methods and parameters for adaptive traffic signal control","author":"El-Tantawy","year":"2011"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2016.7508798"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2018.8500414"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220096"},{"key":"ref28","first-page":"1151","article-title":"Multi-agent reinforcement learning for traffic light control","volume-title":"Proc. 17th Int. Conf. Mach. Learn. (ICML)","author":"Wiering"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2011.6083114"},{"key":"ref30","article-title":"Adaptive traffic signal control: Deep reinforcement learning algorithm with experience replay and target network","author":"Gao","year":"2017","journal-title":"arXiv:1705.02755"},{"key":"ref31","article-title":"Distributed traffic light control at uncoupled intersections with real-world topology by deep reinforcement learning","author":"Schutera","year":"2018","journal-title":"arXiv:1811.11233"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/7503.003.0151"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/WIIAT.2008.88"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1049\/iet-its.2009.0096"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1080\/15472450.2017.1387546"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2907618"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.3390\/s20010137"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2013.2255286"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.23919\/ACC.2017.7963745"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"ref42","article-title":"Prioritized experience replay","author":"Schaul","year":"2015","journal-title":"arXiv:1511.05952"},{"key":"ref43","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Sutton"},{"key":"ref44","first-page":"1889","article-title":"Trust region policy optimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Schulman"},{"key":"ref45","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"},{"key":"ref46","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Mnih"},{"key":"ref47","first-page":"1","article-title":"Continuous control with deep reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Lillicrap"},{"key":"ref48","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Fujimoto"},{"key":"ref49","first-page":"2085","article-title":"Value-decomposition networks for cooperative multi-agent learning based on team reward","volume-title":"Proc. AAMAS","author":"Sunehag"},{"key":"ref50","first-page":"4295","article-title":"QMIX: Monotonic value function factorisation for deep multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Rashid"},{"key":"ref51","first-page":"1","article-title":"Learning when to communicate at scale in multiagent cooperative and competitive tasks","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Singh"},{"key":"ref52","first-page":"1538","article-title":"TarMAC: Targeted multi-agent communication","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Das"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2009.191"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.5555\/2999134.2999257"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2018.8569938"},{"key":"ref56","first-page":"4759","article-title":"Deep reinforcement learning in a handful of trials using probabilistic dynamics models","volume-title":"Proc. 32nd Int. Conf. Neural Inf. Process. Syst.","author":"Chua"}],"container-title":["IEEE Transactions on Intelligent Transportation Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6979\/9853713\/09556580.pdf?arnumber=9556580","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,12]],"date-time":"2024-01-12T00:01:41Z","timestamp":1705017701000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9556580\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,8]]},"references-count":56,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tits.2021.3115240","relation":{},"ISSN":["1524-9050","1558-0016"],"issn-type":[{"value":"1524-9050","type":"print"},{"value":"1558-0016","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,8]]}}}