{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,13]],"date-time":"2025-12-13T09:46:44Z","timestamp":1765619204940,"version":"3.48.0"},"reference-count":40,"publisher":"Springer Science and Business Media LLC","issue":"12","license":[{"start":{"date-parts":[[2025,9,22]],"date-time":"2025-09-22T00:00:00Z","timestamp":1758499200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,9,22]],"date-time":"2025-09-22T00:00:00Z","timestamp":1758499200000},"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":["62306010"],"award-info":[{"award-number":["62306010"]}],"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":["62306010"],"award-info":[{"award-number":["62306010"]}],"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":["62306010"],"award-info":[{"award-number":["62306010"]}],"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":["62306010"],"award-info":[{"award-number":["62306010"]}],"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":["62306010"],"award-info":[{"award-number":["62306010"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int. J. Mach. Learn. & Cyber."],"published-print":{"date-parts":[[2025,12]]},"DOI":"10.1007\/s13042-025-02795-7","type":"journal-article","created":{"date-parts":[[2025,9,22]],"date-time":"2025-09-22T05:54:29Z","timestamp":1758520469000},"page":"10703-10722","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Fusing lane-level flow inference and multi-step RL for adaptive traffic signal coordination"],"prefix":"10.1007","volume":"16","author":[{"given":"Haoran","family":"Cheng","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bo","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jie","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianqing","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tongchun","family":"Du","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,9,22]]},"reference":[{"key":"2795_CR1","doi-asserted-by":"publisher","DOI":"10.7717\/peerj-cs.689","volume":"7","author":"A Abdi","year":"2021","unstructured":"Abdi A, Amrit C (2021) A review of travel and arrival-time prediction methods on road networks: classification, challenges and opportunities. PeerJ Comput Sci 7:e689","journal-title":"PeerJ Comput Sci"},{"key":"2795_CR2","doi-asserted-by":"crossref","unstructured":"Gandhi MM, Solanki DS, Daptardar RS, Baloorkar NS (2020) Smart control of traffic light using artificial intelligence. In: 2020 5th IEEE international conference on recent advances and innovations in engineering (ICRAIE) 1\u20136","DOI":"10.1109\/ICRAIE51050.2020.9358334"},{"key":"2795_CR3","doi-asserted-by":"publisher","first-page":"123","DOI":"10.1016\/j.conengprac.2011.10.002","volume":"20","author":"F Basile","year":"2012","unstructured":"Basile F, Chiacchio P, Teta D (2012) A hybrid model for real time simulation of urban traffic. Control Eng Pract 20:123\u2013137","journal-title":"Control Eng Pract"},{"key":"2795_CR4","doi-asserted-by":"publisher","first-page":"1269","DOI":"10.1049\/itr2.12208","volume":"16","author":"M Mileti\u0107","year":"2022","unstructured":"Mileti\u0107 M, Ivanjko E, Greguri\u0107 M, Ku\u0161i\u0107 K (2022) A review of reinforcement learning applications in adaptive traffic signal control. IET Intel Transport Syst 16:1269\u20131285","journal-title":"IET Intel Transport Syst"},{"key":"2795_CR5","doi-asserted-by":"publisher","first-page":"473","DOI":"10.1016\/j.trb.2020.07.002","volume":"139","author":"A Lopez","year":"2020","unstructured":"Lopez A, Jin W, Al Faruque MA (2020) Security analysis for fixed-time traffic control systems. Transp Res Part B Methodol 139:473\u2013495","journal-title":"Transp Res Part B Methodol"},{"key":"2795_CR6","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s12544-020-00440-8","volume":"12","author":"M Eom","year":"2020","unstructured":"Eom M, Kim B-I (2020) The traffic signal control problem for intersections: a review. Eur Transp Res Rev 12:1\u201320","journal-title":"Eur Transp Res Rev"},{"key":"2795_CR7","doi-asserted-by":"publisher","first-page":"55","DOI":"10.3141\/2438-06","volume":"2438","author":"N Ding","year":"2014","unstructured":"Ding N, He Q, Wu C (2014) Performance measures of manual multimodal traffic signal control. Transp Res Rec 2438:55\u201363","journal-title":"Transp Res Rec"},{"key":"2795_CR8","first-page":"279","volume":"8","author":"CJ Watkins","year":"1992","unstructured":"Watkins CJ, Dayan P (1992) Q-learning. Mach Learn 8:279\u2013292","journal-title":"Mach Learn"},{"key":"2795_CR9","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2024.104663","volume":"164","author":"Y Bie","year":"2024","unstructured":"Bie Y, Ji Y, Ma D (2024) Multi-agent deep reinforcement learning collaborative traffic signal control method considering intersection heterogeneity. Transp Res Part C Emerg Technol 164:104663","journal-title":"Transp Res Part C Emerg Technol"},{"key":"2795_CR10","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2021.103059","volume":"125","author":"Z Li","year":"2021","unstructured":"Li Z, Yu H, Zhang G, Dong S, Xu C-Z (2021) Network-wide traffic signal control optimization using a multi-agent deep reinforcement learning. Transp Res Part C Emerg Technol 125:103059","journal-title":"Transp Res Part C Emerg Technol"},{"key":"2795_CR11","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1038\/nature14236","volume":"518","author":"V Mnih","year":"2015","unstructured":"Mnih V et al (2015) Human-level control through deep reinforcement learning. Nature 518:529\u2013533","journal-title":"Nature"},{"key":"2795_CR12","unstructured":"Van\u00a0der Pol E, Oliehoek FA (2016) Coordinated deep reinforcement learners for traffic light control. In: Proceedings of learning, inference and control of multi-agent systems (at NIPS 2016), vol. 8, pp 21\u201338"},{"key":"2795_CR13","unstructured":"Haarnoja T, Zhou A, Abbeel P, Levine S (2018) Soft actor-critic: off-policy maximum entropy deep reinforcement learning with a stochastic actor. In: International conference on machine learning 1861\u20131870"},{"key":"2795_CR14","unstructured":"Ha D, Schmidhuber J (2018) World models. arXiv preprint arXiv:1803.10122. 2"},{"key":"2795_CR15","unstructured":"Chenguang Z, Xiaorong H, Gang W (2021) Prglight: a novel traffic light control framework with pressure-based-reinforcement learning and graph neural network. In: Proceedings of the International Joint Conference on Artificial Intelligence"},{"key":"2795_CR16","doi-asserted-by":"crossref","unstructured":"Mei H, Li J, Shi B, Wei H (2023) Reinforcement learning approaches for traffic signal control under missing data. In: Proceedings of the 32nd International Joint Conference on Artificial Intelligence, IJCAI 2023 2261\u20132269","DOI":"10.24963\/ijcai.2023\/251"},{"key":"2795_CR17","doi-asserted-by":"crossref","unstructured":"Jiang Q, Li J, Sun W, Zheng B (2021) Dynamic lane traffic signal control with group attention and multi-timescale reinforcement learning. In: Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, IJCAI-21 3642\u20133648","DOI":"10.24963\/ijcai.2021\/501"},{"key":"2795_CR18","first-page":"1","volume":"25","author":"X Zeng","year":"2024","unstructured":"Zeng X, Peng H, Su D, Li A (2024) Hierarchical decision making based on structural information principles. J Mach Learn Res 25:1\u201342","journal-title":"J Mach Learn Res"},{"key":"2795_CR19","doi-asserted-by":"crossref","unstructured":"Zou D et\u00a0al (2024) Multispans: a multi-range spatial-temporal transformer network for traffic forecast via structural entropy optimization. In: Proceedings of the 17th ACM International conference on web search and data mining 1032\u20131041","DOI":"10.1145\/3616855.3635820"},{"key":"2795_CR20","doi-asserted-by":"crossref","unstructured":"Zeng X, Peng H, Li A (2023) Effective and stable role-based multi-agent collaboration by structural information principles. In: Proceedings of the AAAI conference on artificial intelligence, vol. 37, pp 11772\u201311780","DOI":"10.1609\/aaai.v37i10.26390"},{"key":"2795_CR21","first-page":"1","volume":"37","author":"X Zeng","year":"2024","unstructured":"Zeng X, Peng H, Li A (2024) Effective exploration based on the structural information principles. Adv Neural Inf Process Syst (NeurIPS) 37:1\u201315","journal-title":"Adv Neural Inf Process Syst (NeurIPS)"},{"key":"2795_CR22","doi-asserted-by":"crossref","unstructured":"Yen CC, Ghosal D, Zhang M, Chuah CN (2020) A deep on-policy learning agent for traffic signal control of multiple intersections. In: 2020 IEEE 23rd International Conference on Intelligent Transportation Systems (ITSC) 1\u20136. https:\/\/api.semanticscholar.org\/CorpusID:229702162","DOI":"10.1109\/ITSC45102.2020.9294471"},{"key":"2795_CR23","doi-asserted-by":"crossref","unstructured":"Zhao D, Wang H, Shao K, Zhu Y (2016) Deep reinforcement learning with experience replay based on Sarsa. In: 2016 IEEE symposium series on computational intelligence (SSCI) 1\u20136","DOI":"10.1109\/SSCI.2016.7849837"},{"key":"2795_CR24","doi-asserted-by":"publisher","first-page":"895","DOI":"10.1007\/s10462-021-09996-w","volume":"55","author":"S Gronauer","year":"2022","unstructured":"Gronauer S, Diepold K (2022) Multi-agent deep reinforcement learning: a survey. Artif Intell Rev 55:895\u2013943","journal-title":"Artif Intell Rev"},{"key":"2795_CR25","doi-asserted-by":"publisher","first-page":"1803","DOI":"10.1109\/TVT.2023.3319698","volume":"73","author":"L Li","year":"2023","unstructured":"Li L et al (2023) Adaptive multi-agent deep mixed reinforcement learning for traffic light control. IEEE Trans Veh Technol 73:1803\u20131816","journal-title":"IEEE Trans Veh Technol"},{"key":"2795_CR26","unstructured":"Lowe R et\u00a0al (2017) Multi-agent actor-critic for mixed cooperative-competitive environments. Adv Neural Inf Process Syst 30"},{"key":"2795_CR27","first-page":"160","volume":"15","author":"F Mao","year":"2022","unstructured":"Mao F, Li Z, Li L (2022) A comparison of deep reinforcement learning models for isolated traffic signal control. IEEE Intell Transp Syst Mag 15:160\u2013180","journal-title":"IEEE Intell Transp Syst Mag"},{"key":"2795_CR28","doi-asserted-by":"publisher","first-page":"243","DOI":"10.1016\/j.inffus.2023.02.009","volume":"94","author":"S Yang","year":"2023","unstructured":"Yang S, Yang B, Zeng Z, Kang Z (2023) Causal inference multi-agent reinforcement learning for traffic signal control. Inf Fusion 94:243\u2013256","journal-title":"Inf Fusion"},{"key":"2795_CR29","doi-asserted-by":"publisher","first-page":"1086","DOI":"10.1109\/TITS.2019.2901791","volume":"21","author":"T Chu","year":"2019","unstructured":"Chu T, Wang J, Codec\u00e0 L, Li Z (2019) Multi-agent deep reinforcement learning for large-scale traffic signal control. IEEE Trans Intell Transp Syst 21:1086\u20131095","journal-title":"IEEE Trans Intell Transp Syst"},{"key":"2795_CR30","doi-asserted-by":"publisher","first-page":"390","DOI":"10.1016\/j.neucom.2021.11.106","volume":"490","author":"B Liu","year":"2022","unstructured":"Liu B, Ding Z (2022) A distributed deep reinforcement learning method for traffic light control. Neurocomputing 490:390\u2013399","journal-title":"Neurocomputing"},{"key":"2795_CR31","doi-asserted-by":"crossref","unstructured":"Wei H et\u00a0al (2019) Colight: learning network-level cooperation for traffic signal control. In: Proceedings of the 28th ACM international conference on information and knowledge management 1913\u20131922","DOI":"10.1145\/3357384.3357902"},{"key":"2795_CR32","doi-asserted-by":"crossref","unstructured":"Wu Z, Pan S, Long G, Jiang J, Zhang C (2019) Graph wavenet for deep spatial-temporal graph modeling. In: Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence, IJCAI-19 1907\u20131913","DOI":"10.24963\/ijcai.2019\/264"},{"key":"2795_CR33","doi-asserted-by":"publisher","first-page":"2228","DOI":"10.1109\/TMC.2020.3033782","volume":"21","author":"Y Wang","year":"2020","unstructured":"Wang Y et al (2020) Stmarl: a spatio-temporal multi-agent reinforcement learning approach for cooperative traffic light control. IEEE Trans Mob Comput 21:2228\u20132242","journal-title":"IEEE Trans Mob Comput"},{"key":"2795_CR34","first-page":"1","volume":"21","author":"T Rashid","year":"2020","unstructured":"Rashid T et al (2020) Monotonic value function factorisation for deep multi-agent reinforcement learning. J Mach Learn Res 21:1\u201351","journal-title":"J Mach Learn Res"},{"key":"2795_CR35","unstructured":"Son K, Kim D, Kang WJ, Hostallero DE, Yi Y (2019) Qtran: learning to factorize with transformation for cooperative multi-agent reinforcement learning. In: International conference on machine learning, pp 5887\u20135896"},{"key":"2795_CR36","unstructured":"Janner M, Fu J, Zhang M, Levine S (2019) When to trust your model: model-based policy optimization. Adv Neural Inf Process Syst 32"},{"key":"2795_CR37","doi-asserted-by":"crossref","unstructured":"Zang X et al (2020) Metalight: value-based meta-reinforcement learning for traffic signal control. In: Proceedings of the AAAI conference on artificial intelligence, vol. 34, pp 1153\u20131160","DOI":"10.1609\/aaai.v34i01.5467"},{"key":"2795_CR38","doi-asserted-by":"publisher","first-page":"314","DOI":"10.1080\/15472450.2021.2023016","volume":"27","author":"H Wang","year":"2023","unstructured":"Wang H, Yuan Y, Yang XT, Zhao T, Liu Y (2023) Deep q learning-based traffic signal control algorithms: model development and evaluation with field data. J Intell Transp Syst 27:314\u2013334","journal-title":"J Intell Transp Syst"},{"key":"2795_CR39","doi-asserted-by":"publisher","first-page":"328","DOI":"10.1016\/j.conengprac.2011.12.004","volume":"20","author":"ML Darby","year":"2012","unstructured":"Darby ML, Nikolaou M (2012) Mpc: current practice and challenges. Control Eng Pract 20:328\u2013342","journal-title":"Control Eng Pract"},{"key":"2795_CR40","doi-asserted-by":"crossref","unstructured":"Chen C et al (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"}],"container-title":["International Journal of Machine Learning and Cybernetics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13042-025-02795-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s13042-025-02795-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13042-025-02795-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,13]],"date-time":"2025-12-13T09:41:57Z","timestamp":1765618917000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s13042-025-02795-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,22]]},"references-count":40,"journal-issue":{"issue":"12","published-print":{"date-parts":[[2025,12]]}},"alternative-id":["2795"],"URL":"https:\/\/doi.org\/10.1007\/s13042-025-02795-7","relation":{},"ISSN":["1868-8071","1868-808X"],"issn-type":[{"type":"print","value":"1868-8071"},{"type":"electronic","value":"1868-808X"}],"subject":[],"published":{"date-parts":[[2025,9,22]]},"assertion":[{"value":"5 January 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 September 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 September 2025","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"}},{"value":"This article does not contain studies with human participants or animals. Statement of informed consent is not applicable since the manuscript does not contain any patient data.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical and informed consent for data used"}},{"value":"Informed consent for publication was obtained from all participants or their legal guardians.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}}]}}