{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T20:21:53Z","timestamp":1792786913861,"version":"4.5.0"},"reference-count":52,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Smart Traffic Fund"},{"name":"Hong Kong Transport Department","award":["PSRI\/13\/2109\/PR"],"award-info":[{"award-number":["PSRI\/13\/2109\/PR"]}]},{"name":"National Natural Science Foundation of China","award":["52325210"],"award-info":[{"award-number":["52325210"]}],"id":[{"id":"https:\/\/ror.org\/01h0zpd94","id-type":"ROR","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Intell. Transport. Syst."],"published-print":{"date-parts":[[2026,9]]},"DOI":"10.1109\/tits.2026.3694904","type":"journal-article","created":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T19:44:18Z","timestamp":1779911058000},"page":"10850-10865","source":"Crossref","is-referenced-by-count":2,"title":["Modeling Paradigms for Adaptive Decentralized Traffic Control via a Rollout Reinforcement Learning Approach"],"prefix":"10.1109","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2056-7429","authenticated-orcid":false,"given":"Zhongyang","family":"Lu","sequence":"first","affiliation":[{"name":"City University of Hong Kong","place":["Hong Kong, SAR, China"],"department":["Department of Systems Engineering"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2877-357X","authenticated-orcid":false,"given":"Andy H. F.","family":"Chow","sequence":"additional","affiliation":[{"name":"City University of Hong Kong","place":["Hong Kong, SAR, China"],"department":["Department of Systems Engineering"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5149-570X","authenticated-orcid":false,"given":"Zicheng","family":"Su","sequence":"additional","affiliation":[{"name":"Tongji University","place":["Shanghai, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9403-3174","authenticated-orcid":false,"given":"Wanjing","family":"Ma","sequence":"additional","affiliation":[{"name":"Tongji University","place":["Shanghai, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.tra.2024.104170"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2019.2955425"},{"key":"ref3","volume":"1","author":"Bertsekas","year":"2019","journal-title":"Reinforcement Learning and Optimal Control"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1287\/trsc.2017.0754"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.3008612"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1080\/15472450.2013.810991"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3107258"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3305548"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.trb.2022.12.001"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3314409"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3316285"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/OJITS.2024.3376583"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i25.34891"},{"key":"ref14","first-page":"617","article-title":"Model-based reinforcement learning via meta-policy optimization","volume-title":"Proc. Conf. Robot Learn.","author":"Clavera"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2021.103154"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/0191-2615(94)90002-7"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3342651"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2024.3352730"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2019.2901791"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2021.103059"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i4.20378"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2025.105040"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/tnn.1998.712192"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1080\/21680566.2013.785921"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2024.3494251"},{"key":"ref26","first-page":"33177","article-title":"Model-bellman inconsistency for model-based offline reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sun"},{"key":"ref27","first-page":"12519","article-title":"When to trust your model: Model-based policy optimization","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Janner"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.3141\/2088-17"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2019.05.007"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.trb.2017.02.006"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/s11067-005-6663-6"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1002\/SERIES1345"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2017.09.020"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1561\/2200000016"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2021.107663"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2020.102628"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.commtr.2023.100104"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2023.104021"},{"key":"ref40","first-page":"18560","article-title":"Discor: Corrective feedback in reinforcement learning via distribution correction","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Kumar"},{"key":"ref41","volume-title":"Deep Learning","author":"Goodfellow","year":"2016"},{"key":"ref42","volume-title":"Rollout, Policy Iteration, and Distributed Reinforcement Learning","author":"Bertsekas","year":"2021"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2014.02.018"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2025.3532498"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2023.104258"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4419-6142-6_7"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2013.08.014"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330949"},{"key":"ref49","first-page":"6379","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume-title":"Proc. 31st Conf. Adv. Neural Inf. Process. Syst.","author":"Lowe"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2025.105301"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1016\/j.trb.2026.103411"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2021.103264"}],"container-title":["IEEE Transactions on Intelligent Transportation Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6979\/11689643\/11536906.pdf?arnumber=11536906","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T16:18:11Z","timestamp":1790266691000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11536906\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":52,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tits.2026.3694904","relation":{},"ISSN":["1524-9050","1558-0016"],"issn-type":[{"value":"1524-9050","type":"print"},{"value":"1558-0016","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9]]}}}