{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T00:51:12Z","timestamp":1784335872867,"version":"3.55.0"},"reference-count":41,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T00:00:00Z","timestamp":1706745600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T00:00:00Z","timestamp":1706745600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T00:00:00Z","timestamp":1706745600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2022ZD0120002"],"award-info":[{"award-number":["2022ZD0120002"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62233004"],"award-info":[{"award-number":["62233004"]}],"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":["62203112"],"award-info":[{"award-number":["62203112"]}],"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":["62073076"],"award-info":[{"award-number":["62073076"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004608","name":"Natural Science Foundation of Jiangsu Province","doi-asserted-by":"publisher","award":["BK20210216"],"award-info":[{"award-number":["BK20210216"]}],"id":[{"id":"10.13039\/501100004608","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Jiangsu Provincial Key Laboratory of Networked Collective Intelligence","award":["BM2017002"],"award-info":[{"award-number":["BM2017002"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Ind. Inf."],"published-print":{"date-parts":[[2024,2]]},"DOI":"10.1109\/tii.2023.3296887","type":"journal-article","created":{"date-parts":[[2023,8,1]],"date-time":"2023-08-01T18:37:56Z","timestamp":1690915076000},"page":"2762-2775","source":"Crossref","is-referenced-by-count":11,"title":["Applications in Traffic Signal Control: A Distributed Policy Gradient Decomposition Algorithm"],"prefix":"10.1109","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1455-7216","authenticated-orcid":false,"given":"Pengcheng","family":"Dai","sequence":"first","affiliation":[{"name":"Jiangsu Key Laboratory of Networked Collective Intelligence, School of Mathematics, Southeast University, Nanjing, Jiangsu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3755-179X","authenticated-orcid":false,"given":"Wenwu","family":"Yu","sequence":"additional","affiliation":[{"name":"Frontiers Science Center for Mobile Information Communication and Security, School of Mathematics, Southeast University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3065-393X","authenticated-orcid":false,"given":"He","family":"Wang","sequence":"additional","affiliation":[{"name":"Jiangsu Key Laboratory of Networked Collective Intelligence, School of Mathematics, Southeast University, Nanjing, Jiangsu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-4930-6585","authenticated-orcid":false,"given":"Jiahui","family":"Jiang","sequence":"additional","affiliation":[{"name":"School of Cyber Science and Engineering, Southeast University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2019.2929060"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/tii.2021.3131195"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.3008612"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2019.2929020"},{"issue":"4","key":"ref5","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":"ref6","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":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2011.04.011"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/S0191-2615(03)00015-8"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2010.2050688"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2019.2921475"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2019.2933443"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2021.3082639"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2018.04.082"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2016.12.020"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TNSE.2020.3018871"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-008-9062-9"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220096"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1049\/iet-its.2009.0070"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.3015811"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-307-3.50049-6"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2011.6083114"},{"key":"ref23","first-page":"1","article-title":"Coordinated deep reinforcement learners for traffic light control","volume-title":"Proc. Learn. Inference Control Multi-Agent Syst.","author":"Van der Pol","year":"2016"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3357900"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2019.2901791"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3357902"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5744"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11794"},{"key":"ref29","first-page":"1","article-title":"Off-policy multi-agent decomposed policy gradients","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Wang","year":"2021"},{"key":"ref30","first-page":"5541","article-title":"A policy gradient algorithm for learning to learn in multiagent reinforcement learning","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Kim","year":"2021"},{"key":"ref31","article-title":"Scalable centralized deep multi-agent reinforcement learning via policy gradients","author":"Khan","year":"2018"},{"key":"ref32","first-page":"12208","article-title":"Facmac: Factored multi-agent centralised policy gradients","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Peng","year":"2021"},{"key":"ref33","first-page":"12491","article-title":"FOP: Factorizing optimal joint policy of maximum-entropy multi-agent reinforcement learning","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Zhang","year":"2021"},{"key":"ref34","first-page":"1626","article-title":"Finite-time analysis of distributed TD(0) with linear function approximation on multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Doan","year":"2019"},{"key":"ref35","article-title":"Microscopic modeling of traffic flow: Investigation of collision free vehicle dynamics","author":"Krau","year":"1998"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-32460-4"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-15024-6_7"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2008.2009515"},{"key":"ref39","first-page":"1","article-title":"Multi-agent reinforcement learning for networked system control","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Chu","year":"2019"},{"key":"ref40","first-page":"2244","article-title":"Learning multiagent communication with backpropagation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Sukhbaatar","year":"2016"},{"key":"ref41","first-page":"2137","article-title":"Learning to communicate with deep multi-agent reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Foerster","year":"2016"}],"container-title":["IEEE Transactions on Industrial Informatics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9424\/10440649\/10199158.pdf?arnumber=10199158","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,30]],"date-time":"2024-12-30T19:52:46Z","timestamp":1735588366000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10199158\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,2]]},"references-count":41,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tii.2023.3296887","relation":{},"ISSN":["1551-3203","1941-0050"],"issn-type":[{"value":"1551-3203","type":"print"},{"value":"1941-0050","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,2]]}}}