{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T22:22:31Z","timestamp":1784067751217,"version":"3.55.0"},"reference-count":32,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2025,1,28]],"date-time":"2025-01-28T00:00:00Z","timestamp":1738022400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,28]],"date-time":"2025-01-28T00:00:00Z","timestamp":1738022400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Appl Intell"],"published-print":{"date-parts":[[2025,4]]},"DOI":"10.1007\/s10489-024-06208-0","type":"journal-article","created":{"date-parts":[[2025,1,28]],"date-time":"2025-01-28T07:32:44Z","timestamp":1738049564000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Control of traffic network signals based on deep deterministic policy gradients"],"prefix":"10.1007","volume":"55","author":[{"given":"Huifeng","family":"Hu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2079-7606","authenticated-orcid":false,"given":"Shu","family":"Lin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ping","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jungang","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,1,28]]},"reference":[{"key":"6208_CR1","unstructured":"Goldstone JA (2010) The new population bomb: Four population megatrends that will shape the global future"},{"key":"6208_CR2","doi-asserted-by":"publisher","unstructured":"Miao W, Li L, Wang Z (2021) A survey on deep reinforcement learning for traffic signal control. In: 2021 33rd Chinese Control and Decision Conference (CCDC), pp 1092\u20131097. https:\/\/doi.org\/10.1109\/CCDC52312.2021.9601529","DOI":"10.1109\/CCDC52312.2021.9601529"},{"issue":"3","key":"6208_CR3","doi-asserted-by":"publisher","first-page":"846","DOI":"10.1109\/TITS.2011.2114652","volume":"12","author":"S Lin","year":"2011","unstructured":"Lin S, De Schutter B, Xi Y, Hellendoorn H (2011) Fast model predictive control for urban road networks via milp. IEEE Trans Intell Transp Syst 12(3):846\u2013856. https:\/\/doi.org\/10.1109\/TITS.2011.2114652","journal-title":"IEEE Trans Intell Transp Syst"},{"key":"6208_CR4","doi-asserted-by":"publisher","unstructured":"Ramezani M, Haddad J, Geroliminis N (2015) Dynamics of heterogeneity in urban networks: aggregated traffic modeling and hierarchical control. Transportation Research Part B: Methodological 74:1\u201319. https:\/\/doi.org\/10.1016\/j.trb.2014.12.010","DOI":"10.1016\/j.trb.2014.12.010"},{"issue":"3","key":"6208_CR5","doi-asserted-by":"publisher","first-page":"353","DOI":"10.1002\/oca.2148","volume":"36","author":"FA Souza","year":"2015","unstructured":"Souza FA, Camponogara E, Kraus W, Peccin VB (2015) Distributed mpc for urban traffic networks: A simulation-based performance analysis. Optim Control Appl Methods 36(3):353\u2013368","journal-title":"Optim Control Appl Methods"},{"issue":"9","key":"6208_CR6","doi-asserted-by":"publisher","first-page":"3009","DOI":"10.1109\/TITS.2017.2762085","volume":"19","author":"Y Bi","year":"2018","unstructured":"Bi Y, Lu X, Sun Z, Srinivasan D, Sun Z (2018) Optimal type-2 fuzzy system for arterial traffic signal control. IEEE Trans Intell Transp Syst 19(9):3009\u20133027. https:\/\/doi.org\/10.1109\/TITS.2017.2762085","journal-title":"IEEE Trans Intell Transp Syst"},{"key":"6208_CR7","doi-asserted-by":"publisher","unstructured":"Sofronova E (2021) Evolutionary computations for traffic signals optimization. Procedia Computer Science 186:802\u2013811. https:\/\/doi.org\/10.1016\/j.procs.2021.04.202. 14th International Symposium \"Intelligent Systems","DOI":"10.1016\/j.procs.2021.04.202"},{"key":"6208_CR8","unstructured":"Sutton RS (2018) Reinforcement learning: an introduction. A Bradford Book"},{"key":"6208_CR9","doi-asserted-by":"publisher","first-page":"116313","DOI":"10.1016\/j.oceaneng.2023.116313","volume":"289","author":"N Wang","year":"2023","unstructured":"Wang N, Liu Y, Liu J, Jia W, Zhang C (2023) Reinforcement learning swarm of self-organizing unmanned surface vehicles with unavailable dynamics. Ocean Eng 289:116313","journal-title":"Ocean Eng"},{"issue":"7","key":"6208_CR10","doi-asserted-by":"publisher","first-page":"3034","DOI":"10.1109\/TNNLS.2020.3009214","volume":"32","author":"N Wang","year":"2020","unstructured":"Wang N, Gao Y, Zhao H, Ahn CK (2020) Reinforcement learning-based optimal tracking control of an unknown unmanned surface vehicle. IEEE Trans Neural Netw Learn Syst 32(7):3034\u20133045","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"issue":"12","key":"6208_CR11","doi-asserted-by":"publisher","first-page":"5456","DOI":"10.1109\/TNNLS.2021.3056444","volume":"32","author":"N Wang","year":"2021","unstructured":"Wang N, Gao Y, Zhang X (2021) Data-driven performance-prescribed reinforcement learning control of an unmanned surface vehicle. IEEE Trans Neural Netw Learn Syst 32(12):5456\u20135467","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"issue":"2","key":"6208_CR12","doi-asserted-by":"publisher","first-page":"3605","DOI":"10.1109\/TIV.2023.3348134","volume":"9","author":"Y Qu","year":"2024","unstructured":"Qu Y, Chu H, Gao S, Guan J, Yan H, Xiao L, Li SE, Duan J (2024) Rl-driven mppi: Accelerating online control laws calculation with offline policy. IEEE Trans Intell Veh 9(2):3605\u20133616. https:\/\/doi.org\/10.1109\/TIV.2023.3348134","journal-title":"IEEE Trans Intell Veh"},{"key":"6208_CR13","doi-asserted-by":"crossref","unstructured":"Buechel M, Knoll A (2018) Deep reinforcement learning for predictive longitudinal control of automated vehicles. In: 2018 21st International Conference on Intelligent Transportation Systems (ITSC), pp 2391\u20132397. IEEE","DOI":"10.1109\/ITSC.2018.8569977"},{"key":"6208_CR14","doi-asserted-by":"crossref","unstructured":"Kendall A, Hawke J, Janz D, Mazur P, Reda D, Allen J-M, Lam V-D, Bewley A, Shah A (2019) Learning to drive in a day. In: 2019 International Conference on Robotics and Automation (ICRA), pp 8248\u20138254. IEEE","DOI":"10.1109\/ICRA.2019.8793742"},{"issue":"5","key":"6208_CR15","doi-asserted-by":"publisher","first-page":"127","DOI":"10.3390\/robotics12050127","volume":"12","author":"R Chekroun","year":"2023","unstructured":"Chekroun R, Toromanoff M, Hornauer S, Moutarde F (2023) Gri: General reinforced imitation and its application to vision-based autonomous driving. Robotics 12(5):127","journal-title":"Robotics"},{"key":"6208_CR16","unstructured":"Mnih V, Kavukcuoglu K, Silver D, Graves A, Antonoglou I, Wierstra D, Riedmiller M (2013) Playing atari with deep reinforcement learning. arXiv preprint arXiv:1312.5602"},{"key":"6208_CR17","unstructured":"Pol E, Oliehoek FA (2016) Coordinated deep reinforcement learners for traffic light control. Proceedings of learning, inference and control of multi-agent systems (at NIPS 2016) 1"},{"key":"6208_CR18","unstructured":"Casas N (2017) Deep deterministic policy gradient for urban traffic light control. CoRR arxiv:1703.09035"},{"key":"6208_CR19","doi-asserted-by":"publisher","unstructured":"Chu T, Wang J, Codec\u00e0 L, Li Z (2020) Multi-agent deep reinforcement learning for large-scale traffic signal control. IEEE\u00a0Trans Intell Transp Syst 21(3):1086\u20131095. https:\/\/doi.org\/10.1109\/TITS.2019.2901791","DOI":"10.1109\/TITS.2019.2901791"},{"issue":"7","key":"6208_CR20","doi-asserted-by":"publisher","first-page":"7184","DOI":"10.1109\/TITS.2021.3067057","volume":"23","author":"K-F Chu","year":"2021","unstructured":"Chu K-F, Lam AY, Li VO (2021) Traffic signal control using end-to-end off-policy deep reinforcement learning. IEEE Trans Intell Transp Syst 23(7):7184\u20137195","journal-title":"IEEE Trans Intell Transp Syst"},{"issue":"2","key":"6208_CR21","doi-asserted-by":"publisher","first-page":"1187","DOI":"10.1109\/TVT.2021.3069921","volume":"71","author":"A Boukerche","year":"2021","unstructured":"Boukerche A, Zhong D, Sun P (2021) A novel reinforcement learning-based cooperative traffic signal system through max-pressure control. IEEE Trans Veh Technol 71(2):1187\u20131198","journal-title":"IEEE Trans Veh Technol"},{"issue":"2","key":"6208_CR22","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"},{"issue":"1","key":"6208_CR23","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"},{"issue":"2","key":"6208_CR24","doi-asserted-by":"publisher","first-page":"1333","DOI":"10.1109\/TVT.2021.3134329","volume":"71","author":"Z Wang","year":"2021","unstructured":"Wang Z, Zhu H, He M, Zhou Y, Luo X, Zhang N (2021) Gan and multi-agent drl based decentralized traffic light signal control. IEEE Trans Veh Technol 71(2):1333\u20131348","journal-title":"IEEE Trans Veh Technol"},{"key":"6208_CR25","doi-asserted-by":"crossref","unstructured":"Shi S, Chen F (2018) Deep recurrent q-learning method for area traffic coordination control. Journal of Advances in Mathematics and Computer Science 1\u201311","DOI":"10.9734\/JAMCS\/2018\/41281"},{"key":"6208_CR26","unstructured":"Liu M, Deng J, Xu M, Zhang X, Wang W (2017) Cooperative deep reinforcement learning for traffic signal control. In: 23rd ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), Halifax, vol 2017"},{"key":"6208_CR27","doi-asserted-by":"crossref","unstructured":"Riedmiller M (2005) Neural fitted q iteration\u2013first experiences with a data efficient neural reinforcement learning method. In: European Conference on Machine Learning, pp 317\u2013328. Springer","DOI":"10.1007\/11564096_32"},{"key":"6208_CR28","doi-asserted-by":"crossref","unstructured":"Nishi T, Otaki K, Hayakawa K, Yoshimura T (2018) Traffic signal control based on reinforcement learning with graph convolutional neural nets. In: 2018 21st International Conference on Intelligent Transportation Systems (ITSC), pp 877\u2013883. IEEE","DOI":"10.1109\/ITSC.2018.8569301"},{"key":"6208_CR29","unstructured":"Foerster J, Nardelli N, Farquhar G, Afouras T, Torr PH, Kohli P, Whiteson S (2017) Stabilising experience replay for deep multi-agent reinforcement learning. In: International Conference on Machine Learning, pp 1146\u20131155. PMLR"},{"key":"6208_CR30","unstructured":"Calvo JA, Dusparic I (2018) Heterogeneous multi-agent deep reinforcement learning for traffic lights control. In: AICS, pp 2\u201313"},{"key":"6208_CR31","unstructured":"Lin Y, Dai X, Li L, Wang F-Y (2018) An efficient deep reinforcement learning model for urban traffic control. arXiv preprint arXiv:1808.01876"},{"key":"6208_CR32","unstructured":"Schaul T, Quan J, Antonoglou I, Silver D (2015) Prioritized experience replay. arXiv preprint arXiv:1511.05952"}],"container-title":["Applied Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-024-06208-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10489-024-06208-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-024-06208-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,6]],"date-time":"2025-09-06T04:27:01Z","timestamp":1757132821000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10489-024-06208-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1,28]]},"references-count":32,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2025,4]]}},"alternative-id":["6208"],"URL":"https:\/\/doi.org\/10.1007\/s10489-024-06208-0","relation":{},"ISSN":["0924-669X","1573-7497"],"issn-type":[{"value":"0924-669X","type":"print"},{"value":"1573-7497","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1,28]]},"assertion":[{"value":"20 November 2024","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 January 2025","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"No potential conflict of interest was reported by the authors.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflicts of Interest"}},{"value":"Not applicable","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval"}},{"value":"Not applicable","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent to participate"}},{"value":"Not applicable","order":5,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}}],"article-number":"381"}}