{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T19:06:57Z","timestamp":1772910417275,"version":"3.50.1"},"reference-count":33,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Science Foundation of China","doi-asserted-by":"publisher","award":["62271485"],"award-info":[{"award-number":["62271485"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Science Foundation of China","doi-asserted-by":"publisher","award":["62333015"],"award-info":[{"award-number":["62333015"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Science Foundation of China","doi-asserted-by":"publisher","award":["61673366"],"award-info":[{"award-number":["61673366"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Intell. Transport. Syst."],"published-print":{"date-parts":[[2025,1]]},"DOI":"10.1109\/tits.2024.3494251","type":"journal-article","created":{"date-parts":[[2024,11,26]],"date-time":"2024-11-26T18:53:55Z","timestamp":1732647235000},"page":"714-723","source":"Crossref","is-referenced-by-count":5,"title":["A Stochastic Traffic Flow Model-Based Reinforcement Learning Framework For Advanced Traffic Signal Control"],"prefix":"10.1109","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-7924-7064","authenticated-orcid":false,"given":"Yifan","family":"Zhu","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7565-4979","authenticated-orcid":false,"given":"Yisheng","family":"Lv","sequence":"additional","affiliation":[{"name":"State Key Laboratory for Management and Control of Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1056-3926","authenticated-orcid":false,"given":"Shu","family":"Lin","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing, China"}]},{"given":"Jungang","family":"Xu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.trpro.2017.05.282"},{"key":"ref2","volume-title":"Transport in the european union: Current trends and issues","year":"2019"},{"key":"ref3","article-title":"Playing Atari with deep reinforcement learning","volume-title":"arXiv:1312.5602","author":"Mnih","year":"2013"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2016.7508798"},{"key":"ref5","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":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220096"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5744"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.3008612"},{"key":"ref9","first-page":"3319","article-title":"Axiomatic attribution for deep networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sundararajan"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3236386.3241340"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1049\/iet-its.2017.0153"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2003.819610"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4614-6243-9_2"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2019.2901791"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2019.2904742"},{"key":"ref16","first-page":"1","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Lowe"},{"key":"ref17","first-page":"1146","article-title":"Stabilising experience replay for deep multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Foerster"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11794"},{"key":"ref19","first-page":"2961","article-title":"Actor-attention-critic for multi-agent reinforcement learning","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","author":"Iqbal"},{"key":"ref20","volume-title":"Multi-agent control of large-scale transportation systems: A survey","author":"Tarau","year":"2007"},{"key":"ref21","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton","year":"2018"},{"key":"ref22","first-page":"21","article-title":"Coordinated deep reinforcement learners for traffic light control","volume-title":"Proc. Learn., Inference Control Multi-Agent Syst. (NIPS)","volume":"8","author":"Van der Pol"},{"key":"ref23","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":"ref24","doi-asserted-by":"publisher","DOI":"10.1049\/iet-its.2009.0070"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2017.2702388"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2008.4539481"},{"key":"ref27","article-title":"Continuous control with deep reinforcement learning","volume-title":"arXiv:1509.02971","author":"Lillicrap","year":"2015"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1812.05905"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2018.07.075"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.trb.2010.06.003"},{"key":"ref31","article-title":"Deep deterministic policy gradient for urban traffic light control","volume-title":"arXiv:1703.09035","author":"Casas","year":"2017"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3357902"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.trb.2008.02.002"}],"container-title":["IEEE Transactions on Intelligent Transportation Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6979\/10841922\/10768192.pdf?arnumber=10768192","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,15]],"date-time":"2025-01-15T20:18:14Z","timestamp":1736972294000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10768192\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1]]},"references-count":33,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tits.2024.3494251","relation":{},"ISSN":["1524-9050","1558-0016"],"issn-type":[{"value":"1524-9050","type":"print"},{"value":"1558-0016","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1]]}}}