{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T10:06:36Z","timestamp":1784801196938,"version":"3.55.0"},"reference-count":27,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2026,5,2]],"date-time":"2026-05-02T00:00:00Z","timestamp":1777680000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,5,2]],"date-time":"2026-05-02T00:00:00Z","timestamp":1777680000000},"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":["Int. J. ITS Res."],"published-print":{"date-parts":[[2026,8]]},"DOI":"10.1007\/s13177-026-00665-2","type":"journal-article","created":{"date-parts":[[2026,5,2]],"date-time":"2026-05-02T08:58:14Z","timestamp":1777712294000},"page":"1418-1433","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A Dual-Mode Multi-Agent Reinforcement Learning Method for Context-Aware Traffic Control Optimization"],"prefix":"10.1007","volume":"24","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8249-3176","authenticated-orcid":false,"given":"Nhat Quang","family":"Doan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-7829-139X","authenticated-orcid":false,"given":"Nhat Huy","family":"Ly","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8364-487X","authenticated-orcid":false,"given":"Anh Tuan","family":"Giang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-6277-9297","authenticated-orcid":false,"given":"Hoang Ha","family":"Nguyen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,5,2]]},"reference":[{"issue":"2","key":"665_CR1","doi-asserted-by":"publisher","first-page":"865","DOI":"10.1109\/TITS.2014.2345663","volume":"16","author":"Traffic flow prediction with big data","year":"2015","unstructured":"Traffic flow prediction with big data: A deep learning approach. IEEE Trans. Intell. Transp. Syst. 16(2), 865\u2013873 (2015). https:\/\/doi.org\/10.1109\/TITS.2014.2345663","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"665_CR2","doi-asserted-by":"publisher","unstructured":"Emvlight: A multi-agent reinforcement learning framework for an emergency vehicle decentralized routing and traffic signal control system. Transportation Research Part C: Emerging Technologies 146, 103955 (2023). https:\/\/doi.org\/10.1016\/j.trc.2022.103955","DOI":"10.1016\/j.trc.2022.103955"},{"key":"665_CR3","doi-asserted-by":"publisher","unstructured":"Chu, T., Wang, J., Codec\u00e0 , L., Li, Z.: Multi-agent deep reinforcement learning for large-scale traffic signal control. pp. 1086\u20131095 (2020). https:\/\/doi.org\/10.1109\/TITS.2019.2901791","DOI":"10.1109\/TITS.2019.2901791"},{"key":"665_CR4","doi-asserted-by":"crossref","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. 229, 120535 (2023). https:\/\/doi.org\/10.1016\/j.eswa.2023.120535, https:\/\/www.sciencedirect.com\/science\/article\/pii\/S0957417423010370","DOI":"10.1016\/j.eswa.2023.120535"},{"key":"665_CR5","doi-asserted-by":"publisher","unstructured":"Fu, Y., Di, X.: Federated reinforcement learning for adaptive traffic signal control: A case study in new york city. In: 2023 IEEE 26th International Conference on Intelligent Transportation Systems (ITSC), pp. 5738\u20135743 (2023). https:\/\/doi.org\/10.1109\/ITSC57777.2023.10422024","DOI":"10.1109\/ITSC57777.2023.10422024"},{"key":"665_CR6","unstructured":"Genders, W., Razavi, S.: Using a deep reinforcement learning agent for traffic signal control (2016). arXiv:1611.01142"},{"key":"665_CR7","doi-asserted-by":"crossref","unstructured":"Goel, H., Zhang, Y., Damani, M., Sartoretti, G.: Sociallight: Distributed cooperation learning towards network-wide traffic signal control (2023). arXiv:2305.16145","DOI":"10.65109\/GIFG9402"},{"key":"665_CR8","doi-asserted-by":"publisher","unstructured":"Houli, D., Zhiheng, L., Yi, Z.: Multiobjective reinforcement learning for traffic signal control using vehicular ad hoc network. EURASIP J. Adv. Signal Process. 2010, 724035 (2010). https:\/\/doi.org\/10.1155\/2010\/724035","DOI":"10.1155\/2010\/724035"},{"key":"665_CR9","doi-asserted-by":"publisher","unstructured":"Hu, T., Hu, Z., Lu, Z., Wen, X.: Dynamic traffic signal control using mean field multi-agent reinforcement learning in large scale road-networks. IET Intel. Transport Syst. 17(9), 1715\u20131728 (2023). https:\/\/doi.org\/10.1049\/itr2.12364, https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/abs\/10.1049\/itr2.12364","DOI":"10.1049\/itr2.12364"},{"key":"665_CR10","doi-asserted-by":"publisher","unstructured":"Jiang, H., Li, Z., Wei, H., Xiong, X., Ruan, J., Lu, J., Mao, H., Zhao, R.: X-light: cross-city traffic signal control using transformer on transformer as meta multi-agent reinforcement learner (2024). https:\/\/doi.org\/10.24963\/ijcai.2024\/11","DOI":"10.24963\/ijcai.2024\/11"},{"key":"665_CR11","doi-asserted-by":"crossref","unstructured":"Jin, J., Ma, X.: A decentralized traffic light control system based on adaptive learning. IFAC-PapersOnLine 50(1), 5301\u20135306 (2017). https:\/\/doi.org\/10.1016\/j.ifacol.2017.08.958, https:\/\/www.sciencedirect.com\/science\/article\/pii\/S2405896317314301. 20th IFAC World Congress","DOI":"10.1016\/j.ifacol.2017.08.958"},{"key":"665_CR12","doi-asserted-by":"publisher","unstructured":"LA, P., Bhatnagar, S.: Reinforcement learning with function approximation for traffic signal control. IEEE Trans. Intell. Trans. Syst. 12(2), 412\u2013421 (2011). https:\/\/doi.org\/10.1109\/TITS.2010.2091408","DOI":"10.1109\/TITS.2010.2091408"},{"key":"665_CR13","doi-asserted-by":"publisher","first-page":"11724","DOI":"10.1038\/s41598-025-91966-1","volume":"15","author":"M Li","year":"2025","unstructured":"Li, M., Pan, X., Liu, C., et al.: Federated deep reinforcement learning-based urban traffic signal optimal control. Sci. Rep. 15, 11724 (2025). https:\/\/doi.org\/10.1038\/s41598-025-91966-1","journal-title":"Sci. Rep."},{"issue":"9","key":"665_CR14","doi-asserted-by":"publisher","first-page":"1987","DOI":"10.1109\/JAS.2024.124365","volume":"11","author":"Y Li","year":"2024","unstructured":"Li, Y., Zhang, Y., Li, X., Sun, C.: Regional multi-agent cooperative reinforcement learning for city-level traffic grid signal control. IEEE\/CAA Journal of Automatica Sinica 11(9), 1987\u20131998 (2024). https:\/\/doi.org\/10.1109\/JAS.2024.124365","journal-title":"IEEE\/CAA Journal of Automatica Sinica"},{"key":"665_CR15","doi-asserted-by":"publisher","unstructured":"Liu, Y., Luo, G., Yuan, Q., Li, J., Jin, L., Chen, B., Pan, R.: Gplight: Grouped multi-agent reinforcement learning for large-scale traffic signal control. In: Elkind, E. (ed.) Proceedings of the 32nd International Joint Conference on Artificial Intelligence, IJCAI-23, pp. 199\u2013207. International Joint Conferences on Artificial Intelligence Organization (2023). https:\/\/doi.org\/10.24963\/ijcai.2023\/23. Main Track","DOI":"10.24963\/ijcai.2023\/23"},{"key":"665_CR16","unstructured":"Lowe, R., Wu, Y., Tamar, A., Harb, J., Abbeel, P., Mordatch, I.: Multi-agent actor-critic for mixed cooperative-competitive environments. In: Proceedings of the 31st International Conference on Neural Information Processing Systems, NIPS\u201917, pp. 6382\u20136393. Curran Associates Inc., Red Hook, NY, USA (2017)"},{"key":"665_CR17","doi-asserted-by":"crossref","unstructured":"Ly, N.H., Doan, N.Q., Giang, A.T., Le, H.T., Nguyen, H.H., Tran, H.T.: Enhancing urban traffic control with priority-aware multi-objective reinforcement learning. In: 17th International Conference on Knowledge and System Engineering, KSE 2025, Da Lat, Vietnam November 6-8, 2025, pp. 144\u2013149. IEEE (2025)","DOI":"10.1109\/KSE68178.2025.11309580"},{"key":"665_CR18","unstructured":"Parisotto, E., Ba, J., Salakhutdinov, R.: Actor-mimic: Deep multitask and transfer reinforcement learning. In: International Conference on Learning Representations (ICLR) (2015). arXiv:1511.06342"},{"key":"665_CR19","unstructured":"Rafique, M.T., Mustafa, A., Sajid, H.: Reinforcement learning for adaptive traffic signal control: Turn-based and time-based approaches to reduce congestion (2024). arXiv:2408.15751"},{"key":"665_CR20","doi-asserted-by":"publisher","first-page":"75875","DOI":"10.1109\/ACCESS.2023.3296537","volume":"11","author":"T Saiki","year":"2023","unstructured":"Saiki, T., Arai, S.: Flexible traffic signal control via multi-objective reinforcement learning. IEEE Access 11, 75875\u201375883 (2023). https:\/\/doi.org\/10.1109\/ACCESS.2023.3296537","journal-title":"IEEE Access"},{"issue":"6","key":"665_CR21","doi-asserted-by":"publisher","first-page":"2687","DOI":"10.1109\/TCYB.2019.2904742","volume":"50","author":"T Tan","year":"2020","unstructured":"Tan, T., Bao, F., Deng, Y., Jin, A., Dai, Q., Wang, J.: Cooperative deep reinforcement learning for large-scale traffic grid signal control. IEEE Transactions on Cybernetics 50(6), 2687\u20132700 (2020). https:\/\/doi.org\/10.1109\/TCYB.2019.2904742","journal-title":"IEEE Transactions on Cybernetics"},{"key":"665_CR22","unstructured":"Wang, M., Chen, Y., Pang, A., Cai, Y., Chen, C.S., Kan, Y., Pun, M.O.: Vlmlight: Traffic signal control via vision-language meta-control and dual-branch reasoning (2025). arXiv:2505.19486"},{"issue":"6","key":"665_CR23","doi-asserted-by":"publisher","first-page":"2228","DOI":"10.1109\/TMC.2020.3033782","volume":"21","author":"Y Wang","year":"2022","unstructured":"Wang, Y., Xu, T., Niu, X., Tan, C., Chen, E., Xiong, H.: Stmarl: A spatio-temporal multi-agent reinforcement learning approach for cooperative traffic light control. IEEE Trans. Mob. Comput. 21(6), 2228\u20132242 (2022). https:\/\/doi.org\/10.1109\/TMC.2020.3033782","journal-title":"IEEE Trans. Mob. Comput."},{"key":"665_CR24","doi-asserted-by":"publisher","unstructured":"Wei, H., Zheng, G., Yao, H., Li, Z.: Intellilight: A reinforcement learning approach for intelligent traffic light control. In: Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, KDD \u201918, pp. 2496\u20132505. Association for Computing Machinery, New York, NY, USA (2018). https:\/\/doi.org\/10.1145\/3219819.3220096","DOI":"10.1145\/3219819.3220096"},{"key":"665_CR25","unstructured":"Wiering, M.A.: Multi-agent reinforcement learning for traffic light control. In: P.\u00a0Langley (ed.) Proceedings of the Seventeenth International Conference on Machine Learning (ICML 2000), Stanford University, Stanford, CA, USA, June 29 - July 2, 2000, pp. 1151\u20131158. Morgan Kaufmann (2000)"},{"key":"665_CR26","doi-asserted-by":"publisher","unstructured":"Zang, X., Yao, H., Zheng, G., Xu, N., Xu, K., Li, Z.: Metalight: Value-based meta-reinforcement learning for traffic signal control. pp. 1153\u20131160 (2020). https:\/\/doi.org\/10.1609\/aaai.v34i01.5467","DOI":"10.1609\/aaai.v34i01.5467"},{"key":"665_CR27","doi-asserted-by":"publisher","unstructured":"Zhang, Y., Huang, G.: traffic flow prediction model based on deep belief network and genetic algorithm. IET Intel. Transport Syst. 12(6), 533\u2013541 (2018). https:\/\/doi.org\/10.1049\/iet-its.2017.0199, https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/abs\/10.1049\/iet-its.2017.0199","DOI":"10.1049\/iet-its.2017.0199"}],"container-title":["International Journal of Intelligent Transportation Systems Research"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13177-026-00665-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s13177-026-00665-2","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13177-026-00665-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T09:48:49Z","timestamp":1784800129000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s13177-026-00665-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,2]]},"references-count":27,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2026,8]]}},"alternative-id":["665"],"URL":"https:\/\/doi.org\/10.1007\/s13177-026-00665-2","relation":{},"ISSN":["1348-8503","1868-8659"],"issn-type":[{"value":"1348-8503","type":"print"},{"value":"1868-8659","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,2]]},"assertion":[{"value":"4 December 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 April 2026","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 April 2026","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 May 2026","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Not applicable","order":1,"name":"Ethics","label":"Ethics approval and consent to participate","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable","order":2,"name":"Ethics","label":"Consent for publication","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no competing interests.","order":3,"name":"Ethics","label":"Competing interests","group":{"name":"EthicsHeading","label":"Declarations"}}]}}