{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,13]],"date-time":"2026-05-13T17:11:33Z","timestamp":1778692293000,"version":"3.51.4"},"reference-count":41,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2026,2,28]],"date-time":"2026-02-28T00:00:00Z","timestamp":1772236800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,2,28]],"date-time":"2026-02-28T00:00:00Z","timestamp":1772236800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61802286"],"award-info":[{"award-number":["61802286"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Fundamental Research Funds for the Central Universities, JLU","award":["93K172024K27"],"award-info":[{"award-number":["93K172024K27"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int. J. Mach. Learn. & Cyber."],"published-print":{"date-parts":[[2026,4]]},"DOI":"10.1007\/s13042-025-02864-x","type":"journal-article","created":{"date-parts":[[2026,2,28]],"date-time":"2026-02-28T12:12:51Z","timestamp":1772280771000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["DCA2C: Dynamic cooperative A2C-based traffic signal control in multi-intersection environments"],"prefix":"10.1007","volume":"17","author":[{"given":"Qinghan","family":"Huang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lei","family":"Nie","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dandan","family":"Qi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haizhou","family":"Bao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,2,28]]},"reference":[{"issue":"1","key":"2864_CR1","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1109\/TITS.2020.3008612","volume":"23","author":"A Haydari","year":"2020","unstructured":"Haydari A, Y\u0131lmaz Y (2020) Deep reinforcement learning for intelligent transportation systems: a survey. IEEE Trans Intell Transp Syst 23(1):11\u201332","journal-title":"IEEE Trans Intell Transp Syst"},{"issue":"7","key":"2864_CR2","doi-asserted-by":"publisher","first-page":"4484","DOI":"10.3390\/app13074484","volume":"13","author":"\u017d Majstorovi\u0107","year":"2023","unstructured":"Majstorovi\u0107 \u017d, Ti\u0161ljari\u0107 L, Ivanjko E, Cari\u0107 T (2023) Urban traffic signal control under mixed traffic flows: Literature review. Appl Sci 13(7):4484","journal-title":"Appl Sci"},{"issue":"2","key":"2864_CR3","doi-asserted-by":"publisher","first-page":"4656","DOI":"10.1109\/TCE.2023.3328020","volume":"70","author":"P Rani","year":"2024","unstructured":"Rani P, Sharma C, Ramesh JVN, Verma S, Sharma R, Alkhayyat A, Kumar S (2024) Federated learning-based misbehavior detection for the 5g-enabled internet of vehicles. IEEE Trans Consum Electron 70(2):4656\u20134664. https:\/\/doi.org\/10.1109\/TCE.2023.3328020","journal-title":"IEEE Trans Consum Electron"},{"issue":"2","key":"2864_CR4","doi-asserted-by":"publisher","first-page":"4858","DOI":"10.1109\/TCE.2024.3378509","volume":"70","author":"G Yan","year":"2024","unstructured":"Yan G, Liu K, Liu C, Zhang J (2024) Edge intelligence for internet of vehicles: a survey. IEEE Trans Consum Electron 70(2):4858\u20134877. https:\/\/doi.org\/10.1109\/TCE.2024.3378509","journal-title":"IEEE Trans Consum Electron"},{"key":"2864_CR5","doi-asserted-by":"publisher","DOI":"10.1007\/s13042-024-02439-2","author":"T Li","year":"2024","unstructured":"Li T, Yang G, Chu J (2024) Uncertainty-based bootstrapped optimization for offline reinforcement learning. Int J Mach Learni Cybernet. https:\/\/doi.org\/10.1007\/s13042-024-02439-2","journal-title":"Int J Mach Learni Cybernet"},{"issue":"7","key":"2864_CR6","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s13042-023-02067-2","volume":"15","author":"Y Song","year":"2024","unstructured":"Song Y, Bai X, Fan W, Deng Z, Jiang C (2024) Msstn: a multi-scale spatio-temporal network for traffic flow prediction. Int J Mach Learn Cybernet 15(7):1\u201315","journal-title":"Int J Mach Learn Cybernet"},{"key":"2864_CR7","doi-asserted-by":"publisher","first-page":"177","DOI":"10.1016\/j.trc.2013.08.014","volume":"36","author":"P Varaiya","year":"2013","unstructured":"Varaiya P (2013) Max pressure control of a network of signalized intersections. Trans Res Part C Emerg Technol 36:177\u2013195","journal-title":"Trans Res Part C Emerg Technol"},{"issue":"6","key":"2864_CR8","doi-asserted-by":"publisher","first-page":"7180","DOI":"10.1109\/TMC.2023.3332081","volume":"23","author":"Y Zhang","year":"2024","unstructured":"Zhang Y, Yu Z, Zhang J, Wang L, Luan TH, Guo B, Yuen C (2024) Learning decentralized traffic signal controllers with multi-agent graph reinforcement learning. IEEE Trans Mob Comput 23(6):7180\u20137195. https:\/\/doi.org\/10.1109\/TMC.2023.3332081","journal-title":"IEEE Trans Mob Comput"},{"key":"2864_CR9","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2021.103046","volume":"125","author":"T Wang","year":"2021","unstructured":"Wang T, Cao J, Hussain A (2021) Adaptive traffic signal control for large-scale scenario with cooperative group-based multi-agent reinforcement learning. Trans Res part C Emerg Technol 125:103046","journal-title":"Trans Res part C Emerg Technol"},{"issue":"3","key":"2864_CR10","doi-asserted-by":"publisher","first-page":"1086","DOI":"10.1109\/TITS.2019.2901791","volume":"21","author":"T Chu","year":"2020","unstructured":"Chu T, Wang J, Codec\u00e0 L, Li Z (2020) Multi-agent deep reinforcement learning for large-scale traffic signal control. IEEE Trans Intell Transp Syst 21(3):1086\u20131095. https:\/\/doi.org\/10.1109\/TITS.2019.2901791","journal-title":"IEEE Trans Intell Transp Syst"},{"issue":"2","key":"2864_CR11","first-page":"1727","volume":"24","author":"D Xu","year":"2022","unstructured":"Xu D, Li C, Wang D, Gao G (2022) Robustness analysis of discrete state-based reinforcement learning models in traffic signal control. IEEE Trans Intell Transp Syst 24(2):1727\u20131738","journal-title":"IEEE Trans Intell Transp Syst"},{"key":"2864_CR12","first-page":"871","volume":"16","author":"G Tesauro","year":"2003","unstructured":"Tesauro G (2003) Extending q-learning to general adaptive multi-agent systems. Adv Neural Inf Process Syst 16:871\u2013878","journal-title":"Adv Neural Inf Process Syst"},{"key":"2864_CR13","doi-asserted-by":"crossref","unstructured":"Chen C, Wei H, Xu N, Zheng G, Yang M, Xiong Y, Xu K, Li Z (2020) Toward a thousand lights: Decentralized deep reinforcement learning for large-scale traffic signal control. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 3414\u20133421","DOI":"10.1609\/aaai.v34i04.5744"},{"key":"2864_CR14","doi-asserted-by":"crossref","unstructured":"Goel H, Zhang Y, Damani M, Sartoretti G (2023) Sociallight: Distributed cooperation learning towards network-wide traffic signal control. arXiv preprint arXiv:2305.16145","DOI":"10.65109\/GIFG9402"},{"issue":"7","key":"2864_CR15","doi-asserted-by":"publisher","first-page":"1363","DOI":"10.1049\/itr2.12328","volume":"17","author":"Z Wang","year":"2023","unstructured":"Wang Z, Yang K, Li L, Lu Y, Tao Y (2023) Traffic signal priority control based on shared experience multi-agent deep reinforcement learning. IET Intel Transport Syst 17(7):1363\u20131379","journal-title":"IET Intel Transport Syst"},{"key":"2864_CR16","unstructured":"Hunt P, Robertson D, Bretherton R, Royle MC (1982) The scoot on-line traffic signal optimisation technique. Traffic Engineering & Control 23(4)"},{"key":"2864_CR17","volume-title":"Scats-a traffic responsive method of controlling urban traffic","author":"P Lowrie","year":"1990","unstructured":"Lowrie P (1990) Scats-a traffic responsive method of controlling urban traffic. Sales information brochure published by Roads & Traffic Authority, Sydney, Australia"},{"key":"2864_CR18","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-84628-982-8_3","author":"S-B Cools","year":"2013","unstructured":"Cools S-B, Gershenson C, D\u2019Hooghe B (2013) Self-organizing traffic lights: A realistic simulation. Advances Appl Self-organiz syst. https:\/\/doi.org\/10.1007\/978-1-84628-982-8_3","journal-title":"Advances Appl Self-organiz syst"},{"issue":"4","key":"2864_CR19","doi-asserted-by":"publisher","first-page":"4483","DOI":"10.1007\/s10489-022-03643-9","volume":"53","author":"Z Qiao","year":"2023","unstructured":"Qiao Z, Ke L, Wang X (2023) Traffic signal control using a cooperative ewma-based multi-agent reinforcement learning. Appl Intell 53(4):4483\u20134498","journal-title":"Appl Intell"},{"key":"2864_CR20","doi-asserted-by":"crossref","unstructured":"Wei H, Zheng G, Yao H, Li Z (2018) Intellilight: A reinforcement learning approach for intelligent traffic light control. In: Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp. 2496\u20132505","DOI":"10.1145\/3219819.3220096"},{"key":"2864_CR21","doi-asserted-by":"crossref","unstructured":"Wei H, Xu N, Zhang H, Zheng G, Zang X, Chen C, Zhang W, Zhu Y, Xu K, Li Z (2019) Colight: Learning network-level cooperation for traffic signal control. In: Proceedings of the 28th ACM International Conference on Information and Knowledge Management, pp. 1913\u20131922","DOI":"10.1145\/3357384.3357902"},{"key":"2864_CR22","doi-asserted-by":"publisher","first-page":"639","DOI":"10.1613\/jair.1.14819","volume":"78","author":"B Saglam","year":"2023","unstructured":"Saglam B, Mutlu FB, Cicek DC, Kozat SS (2023) Actor prioritized experience replay. J Artif Intell Res 78:639\u2013672","journal-title":"J Artif Intell Res"},{"issue":"7","key":"2864_CR23","doi-asserted-by":"publisher","first-page":"2302","DOI":"10.3390\/s21072302","volume":"21","author":"S Bouktif","year":"2021","unstructured":"Bouktif S, Cheniki A, Ouni A (2021) Traffic signal control using hybrid action space deep reinforcement learning. Sensors 21(7):2302","journal-title":"Sensors"},{"key":"2864_CR24","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2024.108100","volume":"133","author":"H Zhao","year":"2024","unstructured":"Zhao H, Dong C, Cao J, Chen Q (2024) A survey on deep reinforcement learning approaches for traffic signal control. Eng Appl Artif Intell 133:108100","journal-title":"Eng Appl Artif Intell"},{"key":"2864_CR25","doi-asserted-by":"publisher","first-page":"278","DOI":"10.1016\/j.trpro.2022.02.035","volume":"62","author":"K B\u00e1lint","year":"2022","unstructured":"B\u00e1lint K, Tam\u00e1s T, Tam\u00e1s B (2022) Deep reinforcement learning based approach for traffic signal control. Trans Res Proced 62:278\u2013285","journal-title":"Trans Res Proced"},{"key":"2864_CR26","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2022.108304","volume":"241","author":"Q Wu","year":"2022","unstructured":"Wu Q, Wu J, Shen J, Du B, Telikani A, Fahmideh M, Liang C (2022) Distributed agent-based deep reinforcement learning for large scale traffic signal control. Knowl-Based Syst 241:108304","journal-title":"Knowl-Based Syst"},{"key":"2864_CR27","doi-asserted-by":"crossref","unstructured":"Zeng Z (2021) Graphlight: graph-based reinforcement learning for traffic signal control. In: 2021 Ieee 6th International Conference on Computer and Communication Systems (icccs), pp. 645\u2013650. IEEE","DOI":"10.1109\/ICCCS52626.2021.9449147"},{"issue":"3","key":"2864_CR28","doi-asserted-by":"publisher","first-page":"3129","DOI":"10.1109\/TITS.2022.3229477","volume":"24","author":"F Mao","year":"2022","unstructured":"Mao F, Li Z, Lin Y, Li L (2022) Mastering arterial traffic signal control with multi-agent attention-based soft actor-critic model. IEEE Trans Intell Transp Syst 24(3):3129\u20133144","journal-title":"IEEE Trans Intell Transp Syst"},{"key":"2864_CR29","doi-asserted-by":"crossref","unstructured":"Wei H, Chen C, Zheng G, Wu K, Gayah V, Xu K, Li Z (2019) Presslight: Learning max pressure control to coordinate traffic signals in arterial network. In: Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp. 1290\u20131298","DOI":"10.1145\/3292500.3330949"},{"key":"2864_CR30","doi-asserted-by":"crossref","unstructured":"Fang Z, Zhang F, Wang T, Lian X, Chen M (2022) Monitorlight: Reinforcement learning-based traffic signal control using mixed pressure monitoring. In: Proceedings of the 31st ACM International Conference on Information & Knowledge Management, pp. 478\u2013487","DOI":"10.1145\/3511808.3557400"},{"issue":"2","key":"2864_CR31","doi-asserted-by":"publisher","first-page":"1187","DOI":"10.1109\/TVT.2021.3069921","volume":"71","author":"A Boukerche","year":"2022","unstructured":"Boukerche A, Zhong D, Sun P (2022) A novel reinforcement learning-based cooperative traffic signal system through max-pressure control. IEEE Trans Veh Technol 71(2):1187\u20131198. https:\/\/doi.org\/10.1109\/TVT.2021.3069921","journal-title":"IEEE Trans Veh Technol"},{"key":"2864_CR32","doi-asserted-by":"crossref","unstructured":"Han T, Lyu S, Oguchi T (2022) Wavelearner: A knowledge-combined reinforcement learning to understand coordinated traffic signal control along urban arteries. In: 2022 IEEE 25th International Conference on Intelligent Transportation Systems (ITSC), pp. 1167\u20131174 . IEEE","DOI":"10.1109\/ITSC55140.2022.9922269"},{"key":"2864_CR33","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2023.119484","volume":"647","author":"J Liu","year":"2023","unstructured":"Liu J, Qin S, Su M, Luo Y, Wang Y, Yang S (2023) Multiple intersections traffic signal control based on cooperative multi-agent reinforcement learning. Inf Sci 647:119484","journal-title":"Inf Sci"},{"issue":"8","key":"2864_CR34","doi-asserted-by":"publisher","first-page":"7426","DOI":"10.1109\/TVT.2021.3090796","volume":"70","author":"C Zhang","year":"2021","unstructured":"Zhang C, Jin S, Xue W, Xie X, Chen S, Chen R (2021) Independent reinforcement learning for weakly cooperative multiagent traffic control problem. IEEE Trans Veh Technol 70(8):7426\u20137436","journal-title":"IEEE Trans Veh Technol"},{"issue":"1","key":"2864_CR35","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1109\/TETCI.2023.3304948","volume":"8","author":"Z Xiao","year":"2024","unstructured":"Xiao Z, Xing H, Zhao B, Qu R, Luo S, Dai P, Li K, Zhu Z (2024) Deep contrastive representation learning with self-distillation. IEEE Trans Emerg Topics Comput Intell 8(1):3\u201315. https:\/\/doi.org\/10.1109\/TETCI.2023.3304948","journal-title":"IEEE Trans Emerg Topics Comput Intell"},{"key":"2864_CR36","doi-asserted-by":"crossref","unstructured":"Shijie W, Shangbo W (2023) A novel multi-agent deep rl approach for traffic signal control. In: 2023 IEEE International Conference on Pervasive Computing and Communications Workshops and Other Affiliated Events (PerCom Workshops), pp. 15\u201320 . IEEE","DOI":"10.1109\/PerComWorkshops56833.2023.10150326"},{"issue":"7","key":"2864_CR37","doi-asserted-by":"publisher","first-page":"6774","DOI":"10.1109\/TITS.2021.3062072","volume":"23","author":"M Wang","year":"2022","unstructured":"Wang M, Wu L, Li J, He L (2022) Traffic signal control with reinforcement learning based on region-aware cooperative strategy. IEEE Trans Intell Transp Syst 23(7):6774\u20136785. https:\/\/doi.org\/10.1109\/TITS.2021.3062072","journal-title":"IEEE Trans Intell Transp Syst"},{"issue":"1","key":"2864_CR38","doi-asserted-by":"publisher","first-page":"178","DOI":"10.1109\/TITS.2022.3216203","volume":"24","author":"W Zhang","year":"2022","unstructured":"Zhang W, Yan C, Li X, Fang L, Wu Y-J, Li J (2022) Distributed signal control of arterial corridors using multi-agent deep reinforcement learning. IEEE Trans Intell Transp Syst 24(1):178\u2013190","journal-title":"IEEE Trans Intell Transp Syst"},{"key":"2864_CR39","doi-asserted-by":"publisher","first-page":"513","DOI":"10.1016\/j.procs.2017.05.327","volume":"109","author":"S Touhbi","year":"2017","unstructured":"Touhbi S, Babram MA, Nguyen-Huu T, Marilleau N, Hbid ML, Cambier C, Stinckwich S (2017) Adaptive traffic signal control: Exploring reward definition for reinforcement learning. Procedia Comput Sci 109:513\u2013520","journal-title":"Procedia Comput Sci"},{"issue":"6","key":"2864_CR40","doi-asserted-by":"publisher","first-page":"6248","DOI":"10.1007\/s10489-022-03208-w","volume":"53","author":"L Yan","year":"2023","unstructured":"Yan L, Zhu L, Song K, Yuan Z, Yan Y, Tang Y, Peng C (2023) Graph cooperation deep reinforcement learning for ecological urban traffic signal control. Appl Intell 53(6):6248\u20136265","journal-title":"Appl Intell"},{"key":"2864_CR41","doi-asserted-by":"crossref","unstructured":"Lopez PA, Behrisch M, Bieker-Walz L, Erdmann J, Fl\u00f6tter\u00f6d Y-P, Hilbrich R, L\u00fccken L, Rummel J, Wagner P, Wie\u00dfner E (2018) Microscopic traffic simulation using sumo. In: 2018 21st International Conference on Intelligent Transportation Systems (ITSC), pp. 2575\u20132582 . IEEE","DOI":"10.1109\/ITSC.2018.8569938"}],"container-title":["International Journal of Machine Learning and Cybernetics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13042-025-02864-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s13042-025-02864-x","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13042-025-02864-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,13]],"date-time":"2026-05-13T16:20:27Z","timestamp":1778689227000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s13042-025-02864-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,28]]},"references-count":41,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2026,4]]}},"alternative-id":["2864"],"URL":"https:\/\/doi.org\/10.1007\/s13042-025-02864-x","relation":{},"ISSN":["1868-8071","1868-808X"],"issn-type":[{"value":"1868-8071","type":"print"},{"value":"1868-808X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,28]]},"assertion":[{"value":"15 November 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 November 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 February 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no Conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"164"}}