{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,14]],"date-time":"2026-04-14T15:50:41Z","timestamp":1776181841106,"version":"3.50.1"},"reference-count":44,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T00:00:00Z","timestamp":1725148800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T00:00:00Z","timestamp":1725148800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T00:00:00Z","timestamp":1725148800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Intell. Transport. Syst."],"published-print":{"date-parts":[[2024,9]]},"DOI":"10.1109\/tits.2024.3377106","type":"journal-article","created":{"date-parts":[[2024,3,27]],"date-time":"2024-03-27T19:34:39Z","timestamp":1711568079000},"page":"11330-11344","source":"Crossref","is-referenced-by-count":30,"title":["A General Scenario-Agnostic Reinforcement Learning for Traffic Signal Control"],"prefix":"10.1109","volume":"25","author":[{"given":"Haoyuan","family":"Jiang","sequence":"first","affiliation":[{"name":"Sense-Time Research, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4983-9352","authenticated-orcid":false,"given":"Ziyue","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Information Systems, University of Cologne, Köln, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3408-6300","authenticated-orcid":false,"given":"Zhishuai","family":"Li","sequence":"additional","affiliation":[{"name":"Sense-Time Research, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3378-7201","authenticated-orcid":false,"given":"Lei","family":"Bai","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory, Shanghai, China"}]},{"given":"Hangyu","family":"Mao","sequence":"additional","affiliation":[{"name":"Sense-Time Research, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9008-142X","authenticated-orcid":false,"given":"Wolfgang","family":"Ketter","sequence":"additional","affiliation":[{"name":"Department of Information Systems, University of Cologne, Köln, Germany"}]},{"given":"Rui","family":"Zhao","sequence":"additional","affiliation":[{"name":"Sense-Time Research, Beijing, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3447556.3447565"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1287\/isre.2022.1167"},{"issue":"4","key":"ref3","first-page":"190","article-title":"The SCOOT online traffic signal optimisation technique","volume":"23","author":"Hunt","year":"1982","journal-title":"Traffic Eng. Control"},{"key":"ref4","article-title":"SCATS, Sydney co-ordinated adaptive traffic system: A traffic responsive method of controlling urban traffic","author":"Lowrie","year":"1990"},{"key":"ref5","volume-title":"Traffic Signal Timing Manual","author":"Koonce","year":"2008"},{"key":"ref6","first-page":"21","article-title":"Coordinated deep reinforcement learners for traffic light control","volume-title":"Proc. Learn. Inference Control Multi- Agent Syst.","volume":"1","author":"Van der Pol"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220096"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330949"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3068287"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2013.2255286"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3357900"},{"key":"ref12","first-page":"2083","article-title":"Integrating independent and centralized multi-agent reinforcement learning for traffic signal network optimization","volume-title":"Proc. 19th Int. Conf. Auto. Agents MultiAgent Syst.","author":"Zhang"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5744"},{"key":"ref14","first-page":"1","article-title":"MTLight: Efficient multi-task reinforcement learning for traffic signal control","volume-title":"Proc. ICLR 2022 Workshop Gamification Multiagent Solutions","author":"Zhu"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i01.5467"},{"key":"ref16","first-page":"4079","article-title":"Attendlight: Universal attention-based reinforcement learning model for traffic signal control","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Oroojlooy"},{"key":"ref17","article-title":"ADLight: A universal approach of traffic signal control with augmented data using reinforcement learning","author":"Wang","year":"2022","journal-title":"arXiv:2210.13378"},{"key":"ref18","volume-title":"Traffic Engineering","author":"Roess","year":"2004"},{"key":"ref19","first-page":"1","article-title":"VISSIM: A microscopic simulation tool to evaluate actuated signal control including bus priority","volume-title":"Proc. 64th Inst. Transp. Eng. Annu. Meeting","volume":"32","author":"Fellendorf"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/S0968-090X(00)00047-4"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4614-6243-9_2"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.3141\/2421-15"},{"key":"ref23","first-page":"26645","article-title":"Expression might be enough: Representing pressure and demand for reinforcement learning based traffic signal control","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhang"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.116830"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1287\/trsc.2022.1187"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2011.6082823"},{"key":"ref27","article-title":"Deep deterministic policy gradient for urban traffic light control","author":"Casas","year":"2017","journal-title":"arXiv:1703.09035"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1155\/2013\/962869"},{"key":"ref29","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":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2018.8569301"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3357902"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3340531.3411859"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2022.3232711"},{"key":"ref35","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"},{"key":"ref36","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Mnih"},{"key":"ref37","first-page":"4033","article-title":"Deep exploration via bootstrapped DQN","volume-title":"Proc. 30th Int. Conf. Neural Inf. Process. Syst.","author":"Osband"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2019.2901791"},{"key":"ref39","first-page":"1","article-title":"SUMO\u2014 Simulation of Urban MObility: An overview","volume-title":"Proc. 3rd Int. Conf. Adv. Syst. Simul.","author":"Behrisch"},{"key":"ref40","first-page":"1","article-title":"Reinforcement learning benchmarks for traffic signal control","volume-title":"Proc. 35th Conf. Neural Inf. Process. Syst. Datasets Benchmarks Track","author":"Ault"},{"key":"ref41","article-title":"InTAS\u2014 The Ingolstadt traffic scenario for SUMO","author":"Lobo","year":"2020","journal-title":"arXiv:2011.11995"},{"key":"ref42","first-page":"63","article-title":"Mikroskopische modellierung der personenverkehrsnachfrage auf basis von zeitverwendungstageb\u00fcchern","volume":"81","author":"Varschen","year":"2006","journal-title":"Integrierte Mikro-Simulation von Raum-und Verkehrsentwicklung. Theorie, Konzepte, Modelle, Praxis"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2014.6958030"},{"key":"ref44","first-page":"816","article-title":"Feudal multi-agent deep reinforcement learning for traffic signal control","volume-title":"Proc. 19th Int. Conf. Auto. Agents Multiagent Syst. (AAMAS)","author":"Ma"}],"container-title":["IEEE Transactions on Intelligent Transportation Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6979\/10659279\/10481508.pdf?arnumber=10481508","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,10]],"date-time":"2024-09-10T04:28:08Z","timestamp":1725942488000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10481508\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9]]},"references-count":44,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tits.2024.3377106","relation":{},"ISSN":["1524-9050","1558-0016"],"issn-type":[{"value":"1524-9050","type":"print"},{"value":"1558-0016","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,9]]}}}