{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T16:26:48Z","timestamp":1782404808346,"version":"3.54.5"},"reference-count":39,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62466004"],"award-info":[{"award-number":["62466004"]}],"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":["61962007"],"award-info":[{"award-number":["61962007"]}],"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":["62266009"],"award-info":[{"award-number":["62266009"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004774","name":"Guangxi Key Laboratory of Big Data in Finance and Economics","doi-asserted-by":"publisher","award":["FEDOP2022A06"],"award-info":[{"award-number":["FEDOP2022A06"]}],"id":[{"id":"10.13039\/501100004774","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Key Research and Development Projects in Jiangsu Province","award":["BE2021001-2"],"award-info":[{"award-number":["BE2021001-2"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Intell. Transport. Syst."],"published-print":{"date-parts":[[2025,6]]},"DOI":"10.1109\/tits.2025.3560712","type":"journal-article","created":{"date-parts":[[2025,4,23]],"date-time":"2025-04-23T17:58:15Z","timestamp":1745431095000},"page":"8257-8267","source":"Crossref","is-referenced-by-count":4,"title":["Learning Simultaneous and Sequential Decisions in Multi-Agent Systems With Application to Traffic Signal Control"],"prefix":"10.1109","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5662-2106","authenticated-orcid":false,"given":"Haipeng","family":"Zhang","sequence":"first","affiliation":[{"name":"College of Computer Science and Technology, Guangxi University of Science and Technology, Liuzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2309-7282","authenticated-orcid":false,"given":"Zhiwen","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Electronic Engineering, Guangxi University of Science and Technology, Liuzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jilin","family":"Yu","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Guangxi University of Science and Technology, Liuzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruonan","family":"Zhang","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Guangxi University of Science and Technology, Liuzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-9475-9664","authenticated-orcid":false,"given":"Caoqing","family":"Jiang","sequence":"additional","affiliation":[{"name":"School of Big Data and Artificial Intelligence, Guangxi University of Finance and Economics, Nanning, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gongkun","family":"Luo","sequence":"additional","affiliation":[{"name":"School of Electronic Engineering, Guangxi University of Science and Technology, Liuzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9172-6955","authenticated-orcid":false,"given":"Weiwei","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Southeast University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9080-4971","authenticated-orcid":false,"given":"Wanyuan","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Southeast University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10399"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/534"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1609\/icaps.v23i1.13594"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5744"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3447556.3447565"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330949"},{"key":"ref7","article-title":"Diagnosing reinforcement learning for traffic signal control","author":"Zheng","year":"2019","journal-title":"arXiv:1905.04716"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3357902"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/345"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2020.3033782"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCCS52626.2021.9449147"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/535"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2022.109166"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC55140.2022.9921995"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3216203"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3311426"},{"key":"ref17","first-page":"816","article-title":"Feudal multi-agent deep reinforcement learning for traffic signal control","volume-title":"Proc. AAMAS","author":"Ma"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2019.2904742"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i1.16147"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2019.2901791"},{"key":"ref21","first-page":"2083","article-title":"Integrating independent and centralized multi-agent reinforcement learning for traffic signal network optimization","volume-title":"Proc. AAMAS","author":"Zhang"},{"key":"ref22","first-page":"1","article-title":"Order matters: Agent-by-agent policy optimization","volume-title":"Proc. ICLR","author":"Wang"},{"key":"ref23","first-page":"16509","article-title":"Multi-agent reinforcement learning is a sequence modeling problem","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Wen"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671998"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3275883"},{"key":"ref26","first-page":"1551","article-title":"SocialLight: Distributed cooperation learning towards network-wide traffic signal control","volume-title":"Proc. AAMAS","author":"Goel"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2024\/11"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3482254"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3070835"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3262580"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3229477"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599530"},{"key":"ref33","article-title":"Traffic signal control using lightweight transformers: An offline-to-online RL approach","author":"Huang","year":"2023","journal-title":"arXiv:2312.07795"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3357900"},{"key":"ref35","article-title":"Heterogeneous-agent mirror learning: A continuum of solutions to cooperative Marl","author":"Grudzien Kuba","year":"2022","journal-title":"arXiv:2208.01682"},{"key":"ref36","first-page":"24631","article-title":"MANSA: Learning fast and slow in multi-agent systems","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Mguni"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-023-06412-y"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3308558.3314139"},{"key":"ref39","article-title":"A survey on traffic signal control methods","author":"Wei","year":"2019","journal-title":"arXiv:1904.08117"}],"container-title":["IEEE Transactions on Intelligent Transportation Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6979\/11021249\/10975081.pdf?arnumber=10975081","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,3]],"date-time":"2025-06-03T05:45:27Z","timestamp":1748929527000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10975081\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6]]},"references-count":39,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tits.2025.3560712","relation":{},"ISSN":["1524-9050","1558-0016"],"issn-type":[{"value":"1524-9050","type":"print"},{"value":"1558-0016","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6]]}}}