{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,6]],"date-time":"2025-10-06T12:42:13Z","timestamp":1759754533628,"version":"build-2065373602"},"reference-count":31,"publisher":"Springer Science and Business Media LLC","issue":"7","license":[{"start":{"date-parts":[[2025,10,6]],"date-time":"2025-10-06T00:00:00Z","timestamp":1759708800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,10,6]],"date-time":"2025-10-06T00:00:00Z","timestamp":1759708800000},"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":["SN COMPUT. SCI."],"DOI":"10.1007\/s42979-025-04410-6","type":"journal-article","created":{"date-parts":[[2025,10,6]],"date-time":"2025-10-06T12:06:23Z","timestamp":1759752383000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Deep Reinforcement Learning for Traffic Flow Control in Large-Scale Networks"],"prefix":"10.1007","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-4386-5113","authenticated-orcid":false,"given":"Anand","family":"Gokul","sequence":"first","affiliation":[]},{"given":"Sakthi Ganesh","family":"Mahalingam","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,10,6]]},"reference":[{"issue":"6","key":"4410_CR1","doi-asserted-by":"publisher","first-page":"415","DOI":"10.1016\/S0968-090X(00)00047-4","volume":"9","author":"P Mirchandani","year":"2001","unstructured":"Mirchandani P, Head L. A real-time traffic signal control system: architecture, algorithms, and analysis. Transport Res Part C Emerg Technol. 2001;9(6):415\u201332.","journal-title":"Transport Res Part C Emerg Technol"},{"issue":"1","key":"4410_CR2","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1109\/25.69966","volume":"40","author":"DI Robertson","year":"1991","unstructured":"Robertson DI, Bretherton RD. Optimizing networks of traffic signals in real time-the scoot method. IEEE Trans Veh Technol. 1991;40(1):11\u20135.","journal-title":"IEEE Trans Veh Technol"},{"key":"4410_CR3","volume-title":"Scoot-a traffic responsive method of coordinating signals","author":"P Hunt","year":"1981","unstructured":"Hunt P, Robertson D, Bretherton R, Royle M. Scoot-a traffic responsive method of coordinating signals. Publication of: Traffic Engineering & Control; 1981."},{"issue":"2","key":"4410_CR4","doi-asserted-by":"publisher","first-page":"183","DOI":"10.1016\/S0967-0661(01)00121-6","volume":"10","author":"C Diakaki","year":"2002","unstructured":"Diakaki C, Papageorgiou M, Aboudolas K. A multivariable regulator approach to traffic-responsive network-wide signal control. Control Eng Pract. 2002;10(2):183\u201395.","journal-title":"Control Eng Pract"},{"key":"4410_CR5","volume-title":"Scats, Sydney co-ordinated adaptive traffic system: A traffic responsive method of controlling urban traffic","author":"P Lowrie","year":"1990","unstructured":"Lowrie P. Scats, Sydney co-ordinated adaptive traffic system: A traffic responsive method of controlling urban traffic. Darlinghurst: Roads and Traffic Authority NSW; 1990."},{"issue":"2","key":"4410_CR6","doi-asserted-by":"publisher","first-page":"485","DOI":"10.1109\/TITS.2010.2048313","volume":"11","author":"B Chen","year":"2010","unstructured":"Chen B, Cheng HH. A review of the applications of agent technology in traffic and transportation systems. IEEE Trans Intell Transp Syst. 2010;11(2):485\u201397.","journal-title":"IEEE Trans Intell Transp Syst"},{"issue":"5","key":"4410_CR7","first-page":"3828","volume":"37","author":"JJ S\u00e1nchez-Medina","year":"2010","unstructured":"S\u00e1nchez-Medina JJ, Gal\u00e1n-Moreno MJ, Rubio-Royo E. Genetic algorithm-based optimization for traffic signal timing. Expert Syst Appl. 2010;37(5):3828\u201334.","journal-title":"Expert Syst Appl"},{"key":"4410_CR8","doi-asserted-by":"crossref","unstructured":"Eberhart R, Kennedy J. particle swarm optimization. In: Proceedings of the IEEE International Conference on neural networks, Australia, Vol. 1948 1942;","DOI":"10.1109\/ICNN.1995.488968"},{"key":"4410_CR9","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.120535","volume":"229","author":"J Fang","year":"2023","unstructured":"Fang J, You Y, Xu M, Wang J, Cai S. Multi-objective traffic signal control using network-wide agent coordinated reinforcement learning. Expert Syst Appl. 2023;229:120535.","journal-title":"Expert Syst Appl"},{"key":"4410_CR10","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.117921","volume":"207","author":"W Jiang","year":"2022","unstructured":"Jiang W, Luo J. Graph neural network for traffic forecasting: a survey. Expert Syst Appl. 2022;207:117921.","journal-title":"Expert Syst Appl"},{"key":"4410_CR11","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, et al. Distributed agent-based deep reinforcement learning for large scale traffic signal control. Knowl-Based Syst. 2022;241:108304.","journal-title":"Knowl-Based Syst"},{"key":"4410_CR12","unstructured":"Mahalingam AG, Shah A, Gulati A, Mascarenhas R, Panduranga R. Optimizing multi-domain performance with active learning-based improvement strategies. 2023. arXiv:http:\/\/arxiv.org\/abs\/2304.06277."},{"issue":"3","key":"4410_CR13","doi-asserted-by":"publisher","first-page":"247","DOI":"10.1109\/JAS.2016.7508798","volume":"3","author":"L Li","year":"2016","unstructured":"Li L, Lv Y, Wang F-Y. Traffic signal timing via deep reinforcement learning. IEEE\/CAA J Autom Sin. 2016;3(3):247\u201354.","journal-title":"IEEE\/CAA J Autom Sin"},{"issue":"7540","key":"4410_CR14","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1038\/nature14236","volume":"518","author":"V Mnih","year":"2015","unstructured":"Mnih V, Kavukcuoglu K, Silver D, Rusu AA, Veness J, Bellemare MG, et al. Human-level control through deep reinforcement learning. Nature. 2015;518(7540):529\u201333.","journal-title":"Nature"},{"key":"4410_CR15","unstructured":"Van\u00a0der Pol E, Oliehoek FA. Coordinated deep reinforcement learners for traffic light control. In: Proceedings of learning, inference and control of multi-agent systems (at NIPS 2016) 8 2016; 21\u201338."},{"key":"4410_CR16","unstructured":"Genders W, Razavi S. Using a deep reinforcement learning agent for traffic signal control. 2016. arXiv preprint arXiv:1611.01142."},{"key":"4410_CR17","unstructured":"Schulman J, Wolski F, Dhariwal P, Radford A, Klimov O. Proximal policy optimization algorithms. 2017. arXiv preprint arXiv:1707.06347."},{"key":"4410_CR18","unstructured":"Mnih V, Badia AP, Mirza M, Graves A, Lillicrap T, Harley T, Silver D, Kavukcuoglu K. Asynchronous methods for deep reinforcement learning. In: International Conference on machine learning, PMLR, 2016; 1928\u20131937."},{"issue":"3","key":"4410_CR19","doi-asserted-by":"crossref","first-page":"1418","DOI":"10.3390\/s23031418","volume":"23","author":"J Kim","year":"2023","unstructured":"Kim J, Shin S, Jeon J, Ahn C. Cooperative traffic signal control with traffic flow prediction in multi-intersection scenario. Sensors. 2023;23(3):1418.","journal-title":"Sensors"},{"key":"4410_CR20","unstructured":"Wei H, Zheng G, Yao H, Li Z. A survey of traffic signal control methods. 2019. arXiv preprint arXiv:1904.08117."},{"key":"4410_CR21","unstructured":"Krajzewicz D, Erdmann J, Behrisch M, Bieker L. Recent development and applications of sumo-simulation of urban mobility. Int J Adv Syst Meas. 2012;5(3 &4):1\u201311."},{"issue":"2","key":"4410_CR22","doi-asserted-by":"publisher","first-page":"3133","DOI":"10.1007\/s40747-023-01308-9","volume":"10","author":"T Zhang","year":"2024","unstructured":"Zhang T, Cheng J, Zou Y. Multimodal transportation routing optimization based on multi-objective q-learning under time uncertainty. Complex Intell Syst. 2024;10(2):3133\u201352.","journal-title":"Complex Intell Syst"},{"issue":"8","key":"4410_CR23","doi-asserted-by":"publisher","first-page":"8243","DOI":"10.1109\/TVT.2020.2997896","volume":"69","author":"T Wu","year":"2020","unstructured":"Wu T, Zhou P, Liu K, Yuan Y, Wang X, Huang H, et al. Multi-agent deep reinforcement learning for urban traffic light control in vehicular networks. IEEE Trans Veh Technol. 2020;69(8):8243\u201356.","journal-title":"IEEE Trans Veh Technol"},{"key":"4410_CR24","doi-asserted-by":"crossref","unstructured":"Li Y, Zhang C, Zhan F, Liu W, Zhou K, Zheng L. Enhancing traffic signal control through model-based reinforcement learning and policy reuse. 2025. arXiv:https:\/\/arxiv.org\/abs\/2503.08728.","DOI":"10.2139\/ssrn.5191758"},{"key":"4410_CR25","doi-asserted-by":"crossref","unstructured":"Chu T, Wang J. Traffic signal control with macroscopic fundamental diagrams. In: 2015 American Control Conference (ACC), IEEE, 2015; 4380\u20135.","DOI":"10.1109\/ACC.2015.7172018"},{"key":"4410_CR26","doi-asserted-by":"crossref","unstructured":"Tan T, Chu T, Peng B, Wang J. Large-scale traffic grid signal control using decentralized fuzzy reinforcement learning. In: Proceedings of SAI Intelligent Systems Conference (IntelliSys) 2016: Volume 1, Springer, 2018; 652\u2013662.","DOI":"10.1007\/978-3-319-56994-9_44"},{"key":"4410_CR27","doi-asserted-by":"crossref","unstructured":"Abdoos M, Mozayani N, Bazzan AL. Traffic light control in non-stationary environments based on multi agent q-learning. In: 2011 14th International IEEE Conference on intelligent transportation systems (ITSC). IEEE. 2011;1580\u20135.","DOI":"10.1109\/ITSC.2011.6083114"},{"key":"4410_CR28","doi-asserted-by":"publisher","DOI":"10.3390\/electronics11050803","author":"C Mansfield","year":"2022","unstructured":"Mansfield C, Hodgkiss J, Djahel S, Nag A. An efficient detour computation scheme for electric vehicles to support smart cities electrification. Electronics. 2022. https:\/\/doi.org\/10.3390\/electronics11050803.","journal-title":"Electronics."},{"key":"4410_CR29","unstructured":"Ladottraffic counts summary. https:\/\/catalog.data.gov\/dataset\/ladot-traffic-counts-summary. Accessed May 2022."},{"key":"4410_CR30","doi-asserted-by":"crossref","unstructured":"Natarajan S, Tadepalli P. Dynamic preferences in multi-criteria reinforcement learning. In: Proceedings of the 22nd International Conference on Machine learning, 2005; 601\u2013608.","DOI":"10.1145\/1102351.1102427"},{"key":"4410_CR31","doi-asserted-by":"crossref","unstructured":"Vamplew P, Dazeley R, Berry A, Issabekov R, Dekker E. Empirical evaluation methods for multiobjective reinforcement learning algorithms. Mach. Learn. 2010;84:51\u201380.","DOI":"10.1007\/s10994-010-5232-5"}],"container-title":["SN Computer Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42979-025-04410-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s42979-025-04410-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42979-025-04410-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,6]],"date-time":"2025-10-06T12:06:33Z","timestamp":1759752393000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s42979-025-04410-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,6]]},"references-count":31,"journal-issue":{"issue":"7","published-online":{"date-parts":[[2025,10]]}},"alternative-id":["4410"],"URL":"https:\/\/doi.org\/10.1007\/s42979-025-04410-6","relation":{},"ISSN":["2661-8907"],"issn-type":[{"value":"2661-8907","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,6]]},"assertion":[{"value":"14 October 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 September 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 October 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 that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of Interest"}}],"article-number":"876"}}