{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,18]],"date-time":"2026-04-18T18:18:45Z","timestamp":1776536325880,"version":"3.51.2"},"reference-count":46,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2022,7,1]],"date-time":"2022-07-01T00:00:00Z","timestamp":1656633600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,7,1]],"date-time":"2022-07-01T00:00:00Z","timestamp":1656633600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,7,1]],"date-time":"2022-07-01T00:00:00Z","timestamp":1656633600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001659","name":"Deutsche Forschungsgemeinschaft (DFG) through the project \u201cOptimization and Network Wide Analysis of Traffic Signal Control\u201d","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001659","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002322","name":"Coordena\u00e7\u00e3o de Aperfei\u00e7oamento de Pessoal de N\u00edvel Superior-Brasil","doi-asserted-by":"publisher","award":["001"],"award-info":[{"award-number":["001"]}],"id":[{"id":"10.13039\/501100002322","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003593","name":"Brazilian Research Council, Conselho Nacional de Desenvolvimento Cient\u00b4lfico e Tecnol\u00f3gico","doi-asserted-by":"publisher","award":["140500\/2021-9"],"award-info":[{"award-number":["140500\/2021-9"]}],"id":[{"id":"10.13039\/501100003593","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003593","name":"Brazilian Research Council, CNPq","doi-asserted-by":"publisher","award":["307215\/2017-2"],"award-info":[{"award-number":["307215\/2017-2"]}],"id":[{"id":"10.13039\/501100003593","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Intell. Transport. Syst."],"published-print":{"date-parts":[[2022,7]]},"DOI":"10.1109\/tits.2021.3091014","type":"journal-article","created":{"date-parts":[[2021,6,29]],"date-time":"2021-06-29T19:50:37Z","timestamp":1624996237000},"page":"9126-9135","source":"Crossref","is-referenced-by-count":29,"title":["Using Reinforcement Learning to Control Traffic Signals in a Real-World Scenario: An Approach Based on Linear Function Approximation"],"prefix":"10.1109","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5465-4390","authenticated-orcid":false,"given":"Lucas N.","family":"Alegre","sequence":"first","affiliation":[{"name":"Institute of Informatics, Federal University of Rio Grande do Sul, Porto Alegre, Brazil"}]},{"given":"Theresa","family":"Ziemke","sequence":"additional","affiliation":[{"name":"Transport Systems Planning and Transport Telematics Department, Technische Universität Berlin, Berlin, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2803-9607","authenticated-orcid":false,"given":"Ana L. C.","family":"Bazzan","sequence":"additional","affiliation":[{"name":"Institute of Informatics, Federal University of Rio Grande do Sul, Porto Alegre, Brazil"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton","year":"2018"},{"key":"ref2","first-page":"1","article-title":"True online temporal-difference learning","volume":"17","author":"van Seijen","year":"2016","journal-title":"J. Mach. Learn. Res."},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v25i1.7903"},{"key":"ref4","doi-asserted-by":"crossref","DOI":"10.5334\/baw","volume-title":"The Multi-Agent Transport Simulation MATSim","author":"Horni","year":"2016"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1088\/1742-5468\/2008\/04\/P04019"},{"key":"ref6","first-page":"571","article-title":"Adaptive signal control\u2014An overview","volume-title":"Proc. 9th Meeting Euro Work. Group Transp.","author":"Friedrich"},{"key":"ref7","article-title":"Arterial signal timing optimization using PASSER-II","author":"Chang","year":"1988"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/S1474-6670(17)62577-1"},{"key":"ref9","first-page":"75","article-title":"OPAC\u2014A demand-responsive strategy for traffic signal control","volume":"906","author":"Gartner","year":"1983","journal-title":"Transp. Res. Rec."},{"issue":"1","key":"ref10","first-page":"29","article-title":"Self-organizing traffic lights","volume":"16","author":"Gershenson","year":"2005","journal-title":"Complex Syst."},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/S0967-0661(01)00121-6"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2009.04.022"},{"key":"ref13","first-page":"67","article-title":"The Sydney co-ordinated adaptive traffic system: Principles, methodology, algorithms","volume-title":"Proc. Int. Conf. Road Traffic Signalling","author":"Lowrie"},{"key":"ref14","article-title":"SCOOT\u2014A traffic responsive method of coordinating signals","author":"Hunt","year":"1981"},{"key":"ref15","article-title":"Self-stabilizing decentralized signal control of realistic, saturated network traffic","author":"L\u00e4mmer","year":"2010"},{"key":"ref16","first-page":"143","article-title":"Die selbst-steuerung im praxistest","volume":"3","author":"L\u00e4mmer","year":"2016","journal-title":"Stra\u00dfenverkehrstechnik"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2018.04.086"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.trpro.2018.12.215"},{"issue":"3","key":"ref19","doi-asserted-by":"crossref","first-page":"279","DOI":"10.1007\/BF00992698","article-title":"Q-learning","volume":"8","author":"Watkins","year":"1992","journal-title":"Mach. Learn."},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-008-9062-9"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-25808-9_4"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3447556.3447565"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3068287"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2011.6082823"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/COMSNETS.2015.7098712"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-013-0455-3"},{"key":"ref27","article-title":"Playing atari with deep reinforcement learning","volume-title":"NIPS Deep Learn. Workshop","author":"Mnih"},{"key":"ref28","article-title":"Deep reinforcement learning for coordination in traffic light control","author":"Van Der Pol","year":"2016"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/9.580874"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-377-6.50013-X"},{"key":"ref31","article-title":"Traffic signal setting","author":"Webster","year":"1958"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2017.09.020"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1049\/iet-its.2009.0096"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2013.2255286"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/WIIAT.2008.88"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220096"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2019.04.120"},{"key":"ref38","article-title":"Extension of a multi-agent transport simulation for traffic signal control and air transport systems","author":"Grether","year":"2014"},{"key":"ref39","first-page":"11","article-title":"Traffic-actuated signal control: Simulation of the user benefits in a big event real-world scenario","volume-title":"Proc. 2nd Int. Conf. Models Technol. ITS","author":"Grether"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.5334\/baw.12"},{"key":"ref41","article-title":"True online TD($\\lambda$\n)","volume-title":"Proc. 31st Int. Conf. Mach. Learn. (ICML)","author":"Van Seijen"},{"key":"ref42","first-page":"1","article-title":"True online temporal-difference learning","volume":"17","author":"van Seijen","year":"2016","journal-title":"J. Mach. Learn. Res."},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2018.04.008"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2019.04.113"},{"issue":"9","key":"ref45","first-page":"55","article-title":"A reinforcement learning approach with Fourier basis linear function approximation for traffic signal control","volume-title":"Proc. 11th Workshop Agents Traffic Transp. (ATT)","volume":"2701","author":"Ziemke"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.3233\/AIC-201580"}],"container-title":["IEEE Transactions on Intelligent Transportation Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6979\/9826234\/09468362.pdf?arnumber=9468362","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,11]],"date-time":"2024-01-11T23:26:04Z","timestamp":1705015564000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9468362\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7]]},"references-count":46,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tits.2021.3091014","relation":{},"ISSN":["1524-9050","1558-0016"],"issn-type":[{"value":"1524-9050","type":"print"},{"value":"1558-0016","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,7]]}}}