{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T03:18:38Z","timestamp":1769915918770,"version":"3.49.0"},"reference-count":50,"publisher":"Springer Science and Business Media LLC","issue":"7","license":[{"start":{"date-parts":[[2025,5,21]],"date-time":"2025-05-21T00:00:00Z","timestamp":1747785600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,5,21]],"date-time":"2025-05-21T00:00:00Z","timestamp":1747785600000},"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":["Mach Learn"],"published-print":{"date-parts":[[2025,7]]},"DOI":"10.1007\/s10994-025-06785-2","type":"journal-article","created":{"date-parts":[[2025,5,21]],"date-time":"2025-05-21T17:06:14Z","timestamp":1747847174000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["FLight: optimization algorithm for traffic lights based on short-term traffic state forecast"],"prefix":"10.1007","volume":"114","author":[{"given":"Daimin","family":"Liu","sequence":"first","affiliation":[]},{"given":"Jian","family":"Huang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,5,21]]},"reference":[{"key":"6785_CR1","doi-asserted-by":"publisher","first-page":"732","DOI":"10.1016\/j.trc.2017.09.020","volume":"85","author":"M Aslani","year":"2017","unstructured":"Aslani, M., Mesgari, M. S., & Wiering, M. (2017). Adaptive traffic signal control with actor-critic methods in a real-world traffic network with different traffic disruption events. Transportation Research Part C: Emerging Technologies, 85, 732\u2013752.","journal-title":"Transportation Research Part C: Emerging Technologies"},{"key":"6785_CR2","unstructured":"Bai, S., Kolter, J. Z., & Koltun, V. (2018). An empirical evaluation of generic convolutional and recurrent networks for sequence modeling. arXiv:1803.01271"},{"key":"6785_CR3","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2023.110440","volume":"267","author":"S Bouktif","year":"2023","unstructured":"Bouktif, S., Cheniki, A., Ouni, A., & El-Sayed, H. (2023). Deep reinforcement learning for traffic signal control with consistent state and reward design approach. Knowledge-Based Systems, 267, Article 110440.","journal-title":"Knowledge-Based Systems"},{"issue":"1","key":"6785_CR4","doi-asserted-by":"publisher","first-page":"233","DOI":"10.1109\/TASE.2010.2061842","volume":"8","author":"E Camponogara","year":"2010","unstructured":"Camponogara, E., & Scherer, H. F. (2010). Distributed optimization for model predictive control of linear dynamic networks with control-input and output constraints. IEEE Transactions on Automation Science and Engineering, 8(1), 233\u2013242.","journal-title":"IEEE Transactions on Automation Science and Engineering"},{"key":"6785_CR5","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":"6785_CR6","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 IJCAI."},{"key":"6785_CR7","doi-asserted-by":"crossref","unstructured":"Cho, K., Van\u00a0Merri\u00ebnboer, B., Gulcehre, C., Bahdanau, D., Bougares, F., Schwenk, H., & Bengio, Y. (2014). Learning phrase representations using rnn encoder-decoder for statistical machine translation. arXiv:1406.1078","DOI":"10.3115\/v1\/D14-1179"},{"key":"6785_CR8","doi-asserted-by":"crossref","unstructured":"Cools, S.-B., Gershenson, C., spsampsps D\u2019Hooghe, B. (2013). Self-organizing traffic lights: A realistic simulation. In Advances in applied self-organizing systems (pp. 45\u201355).","DOI":"10.1007\/978-1-4471-5113-5_3"},{"key":"6785_CR9","doi-asserted-by":"crossref","unstructured":"El-Tantawy, S., & Abdulhai, B. (2010). An agent-based learning towards decentralized and coordinated traffic signal control. In 13th International IEEE conference on intelligent transportation systems (pp. 665\u2013670). IEEE.","DOI":"10.1109\/ITSC.2010.5625066"},{"issue":"4","key":"6785_CR10","doi-asserted-by":"publisher","first-page":"23","DOI":"10.1002\/cplx.20392","volume":"17","author":"C Gershenson","year":"2012","unstructured":"Gershenson, C., & Rosenblueth, D. A. (2012). Self-organizing traffic lights at multiple-street intersections. Complexity, 17(4), 23\u201339.","journal-title":"Complexity"},{"key":"6785_CR11","unstructured":"Goel, H., Zhang, Y., Damani, M., & Sartoretti, G. (2023). Sociallight: Distributed cooperation learning towards network-wide traffic signal control. arXiv:2305.16145"},{"key":"6785_CR12","doi-asserted-by":"crossref","unstructured":"Han, X., Zhao, X., Zhang, L., & Wang, W. (2023). Mitigating action hysteresis in traffic signal control with traffic predictive reinforcement learning. In Proceedings of the 29th ACM SIGKDD conference on knowledge discovery and data mining (pp. 673\u2013684).","DOI":"10.1145\/3580305.3599528"},{"key":"6785_CR13","unstructured":"Hassanjani, M., Alamiyan-Harandi, F., & Ramazi, P. (2023). Inequity aversion reduces travel time in the traffic light control problem. arXiv:2302.12053"},{"key":"6785_CR14","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735","volume-title":"Long short-term memory","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S. (1997). Long short-term memory. Neural Computation MIT-Press."},{"key":"6785_CR15","unstructured":"Huang, X., Member, D. W., & Boulet, B. (2024). Goal-conditioned data augmentation for offline reinforcement learning. arXiv:2412.20519"},{"key":"6785_CR16","unstructured":"Hunt, P., Robertson, D., Bretherton, R., & Royle, M. C. (1982). The scoot on-line traffic signal optimisation technique. Traffic Engineering and Control23(4)."},{"key":"6785_CR17","doi-asserted-by":"crossref","unstructured":"Jiang, C.-Y., Hu, X.-M., & Chen, W.-N. (2021). An urban traffic signal control system based on traffic flow prediction. In 2021 13th international conference on advanced computational intelligence (ICACI) (pp. 259\u2013265). IEEE.","DOI":"10.1109\/ICACI52617.2021.9435905"},{"key":"6785_CR18","unstructured":"Kipf, T. N., & Welling, M. (2016). Semi-supervised classification with graph convolutional networks. arXiv:1609.02907"},{"key":"6785_CR19","unstructured":"Koonce, P., et al. (2008). Traffic signal timing manual. Technical report: United States. Federal Highway Administration."},{"key":"6785_CR20","unstructured":"Lai, S., Xu, Z., Zhang, W., Liu, H., & Xiong, H. (2023). Large language models as traffic signal control agents: Capacity and opportunity. arXiv:2312.16044"},{"key":"6785_CR21","doi-asserted-by":"publisher","first-page":"431","DOI":"10.1016\/j.trc.2014.11.009","volume":"58","author":"T Le","year":"2015","unstructured":"Le, T., Kov\u00e1cs, P., Walton, N., Vu, H. L., Andrew, L. L., & Hoogendoorn, S. S. (2015). Decentralized signal control for urban road networks. Transportation Research Part C: Emerging Technologies, 58, 431\u2013450.","journal-title":"Transportation Research Part C: Emerging Technologies"},{"key":"6785_CR22","doi-asserted-by":"crossref","unstructured":"Li, L., Li, R., Peng, Y., Huang, C., & Yuan, J. (2022). Cooperative max-pressure enhanced traffic signal control. In Proceedings of the 31st ACM international conference on information and knowledge management (pp. 4173\u20134177).","DOI":"10.1145\/3511808.3557569"},{"key":"6785_CR23","doi-asserted-by":"crossref","unstructured":"Lopez, P. A., 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"},{"key":"6785_CR24","unstructured":"Lowrie, P. (1990). Scats, sydney co-ordinated adaptive traffic system: A traffic responsive method of controlling urban traffic."},{"issue":"2","key":"6785_CR25","doi-asserted-by":"publisher","first-page":"233","DOI":"10.1007\/s11633-022-1383-7","volume":"20","author":"L Meng","year":"2023","unstructured":"Meng, L., Wen, M., Le, C., Li, X., Xing, D., Zhang, W., Wen, Y., Zhang, H., Wang, J., Yang, Y., et al. (2023). Offline pre-trained multi-agent decision transformer. Machine Intelligence Research, 20(2), 233\u2013248.","journal-title":"Machine Intelligence Research"},{"issue":"7540","key":"6785_CR26","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, A. A., Veness, J., Bellemare, M. G., Graves, A., Riedmiller, M., Fidjeland, A. K., Ostrovski, G., et al. (2015). Human-level control through deep reinforcement learning. Nature, 518(7540), 529\u2013533.","journal-title":"Nature"},{"key":"6785_CR27","first-page":"4079","volume":"33","author":"A Oroojlooy","year":"2020","unstructured":"Oroojlooy, A., Nazari, M., Hajinezhad, D., & Silva, J. (2020). Attendlight: Universal attention-based reinforcement learning model for traffic signal control. Advances in Neural Information Processing Systems, 33, 4079\u20134090.","journal-title":"Advances in Neural Information Processing Systems"},{"issue":"18","key":"6785_CR28","doi-asserted-by":"publisher","first-page":"117","DOI":"10.1177\/0361198118786840","volume":"2672","author":"X Sun","year":"2018","unstructured":"Sun, X., & Yin, Y. (2018). A simulation study on max pressure control of signalized intersections. Transportation Research Record, 2672(18), 117\u2013127.","journal-title":"Transportation Research Record"},{"key":"6785_CR29","doi-asserted-by":"crossref","unstructured":"Van\u00a0Hasselt, H., Guez, A., & Silver, D. (2016). Deep reinforcement learning with double q-learning. In Proceedings of the AAAI conference on artificial intelligence (Vol. 30).","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"6785_CR30","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. Transportation Research Part C: Emerging Technologies, 36, 177\u2013195.","journal-title":"Transportation Research Part C: Emerging Technologies"},{"key":"6785_CR31","unstructured":"Vaswani, A. (2017). Attention is all you need. In Advances in neural information processing systems."},{"key":"6785_CR32","unstructured":"Veli\u010dkovi\u0107, P., Cucurull, G., Casanova, A., Romero, A., Lio, P., & Bengio, Y. (2017). Graph attention networks. arXiv:1710.10903"},{"key":"6785_CR33","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 and data mining (pp. 1290\u20131298 ).","DOI":"10.1145\/3292500.3330949"},{"key":"6785_CR34","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":"6785_CR35","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 and data mining (pp. 2496\u20132505)","DOI":"10.1145\/3219819.3220096"},{"issue":"2","key":"6785_CR36","doi-asserted-by":"publisher","first-page":"12","DOI":"10.1145\/3447556.3447565","volume":"22","author":"H Wei","year":"2021","unstructured":"Wei, H., Zheng, G., Gayah, V., & Li, Z. (2021). Recent advances in reinforcement learning for traffic signal control: A survey of models and evaluation. ACM SIGKDD Explorations Newsletter, 22(2), 12\u201318.","journal-title":"ACM SIGKDD Explorations Newsletter"},{"key":"6785_CR37","unstructured":"Wu, Q., Li, M., Shen, J., Du, B., Zheng, H., & Wang, J. (2024). Offlinelight: An offline reinforcement learning model for traffic signal control. In International conference on learning representations."},{"key":"6785_CR38","doi-asserted-by":"crossref","unstructured":"Wu, Q., Li, M., Shen, J., L\u00fc, L., Du, B., & Zhang, K. (2023). Transformerlight: A novel sequence modeling based traffic signaling mechanism via gated transformer. In Proceedings of the 29th ACM SIGKDD conference on knowledge discovery and data mining (pp. 2639\u20132647).","DOI":"10.1145\/3580305.3599530"},{"key":"6785_CR39","unstructured":"Wu, Q., Zhang, L., Shen, J., L\u00fc, L., Du, B., & Wu, J. (2021). Efficient pressure: Improving efficiency for signalized intersections. arXiv:2112.02336"},{"key":"6785_CR40","doi-asserted-by":"crossref","unstructured":"Xiong, Y., Zheng, G., Xu, K., & Li, Z. (2019). Learning traffic signal control from demonstrations. In Proceedings of the 28th ACM international conference on information and knowledge management (pp. 2289\u20132292).","DOI":"10.1145\/3357384.3358079"},{"key":"6785_CR41","doi-asserted-by":"publisher","first-page":"55","DOI":"10.1016\/j.ins.2023.03.087","volume":"634","author":"S Yang","year":"2023","unstructured":"Yang, S. (2023). Hierarchical graph multi-agent reinforcement learning for traffic signal control. Information Sciences, 634, 55\u201372.","journal-title":"Information Sciences"},{"issue":"1","key":"6785_CR42","doi-asserted-by":"publisher","first-page":"79","DOI":"10.53106\/160792642024012501007","volume":"25","author":"Z Yang","year":"2024","unstructured":"Yang, Z., Kong, Y., & Hsia, C.-H. (2024). Derlight: A deep reinforcement learning traffic light control algorithm with dual experience replay. Journal of Internet Technology, 25(1), 79\u201386.","journal-title":"Journal of Internet Technology"},{"key":"6785_CR43","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2022.103991","volume":"149","author":"M Yazdani","year":"2023","unstructured":"Yazdani, M., Sarvi, M., Bagloee, S. A., Nassir, N., Price, J., & Parineh, H. (2023). Intelligent vehicle pedestrian light (ivpl): A deep reinforcement learning approach for traffic signal control. Transportation Research Part C: Emerging Technologies, 149, Article 103991.","journal-title":"Transportation Research Part C: Emerging Technologies"},{"key":"6785_CR44","doi-asserted-by":"crossref","unstructured":"Zang, X., Yao, H., Zheng, G., Xu, N., Xu, K., & Li, Z. (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":"6785_CR45","unstructured":"Zhang, L., & Deng, J. (2023). Data might be enough: Bridge real-world traffic signal control using offline reinforcement learning. arXiv:2303.10828"},{"key":"6785_CR46","doi-asserted-by":"crossref","unstructured":"Zhang, H., Feng, S., Liu, C., Ding, Y., Zhu, Y., Zhou, Z., Zhang, W., Yu, Y., Jin, H., & Li, Z. (2019). Cityflow: A multi-agent reinforcement learning environment for large scale city traffic scenario. In The world wide web conference (pp. 3620\u20133624).","DOI":"10.1145\/3308558.3314139"},{"key":"6785_CR47","doi-asserted-by":"crossref","unstructured":"Zhang, L., Xie, S., spsampsps Deng, J. (2023). Leveraging queue length and attention mechanisms for enhanced traffic signal control optimization. In Joint European conference on machine learning and knowledge discovery in databases (pp. 141\u2013156). Springer.","DOI":"10.1007\/978-3-031-43430-3_9"},{"key":"6785_CR48","unstructured":"Zhao, C., Hu, X., & Wang, G. (2020). Pdlight: A deep reinforcement learning traffic light control algorithm with pressure and dynamic light duration. arXiv:2009.13711"},{"key":"6785_CR49","doi-asserted-by":"crossref","unstructured":"Zheng, G., Xiong, Y., Zang, X., Feng, J., Wei, H., Zhang, H., Li, Y., Xu, K., & Li, Z. (2019). Learning phase competition for traffic signal control. In Proceedings of the 28th ACM international conference on information and knowledge management (pp. 1963\u20131972).","DOI":"10.1145\/3357384.3357900"},{"key":"6785_CR50","doi-asserted-by":"crossref","unstructured":"Zheng, G., Zang, X., Xu, N., Wei, H., Yu, Z., Gayah, V., Xu, K., & Li, Z. (2019). Diagnosing reinforcement learning for traffic signal control. arXiv:1905.04716","DOI":"10.1145\/3357384.3357900"}],"container-title":["Machine Learning"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10994-025-06785-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10994-025-06785-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10994-025-06785-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,6]],"date-time":"2025-09-06T15:12:20Z","timestamp":1757171540000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10994-025-06785-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,21]]},"references-count":50,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2025,7]]}},"alternative-id":["6785"],"URL":"https:\/\/doi.org\/10.1007\/s10994-025-06785-2","relation":{},"ISSN":["0885-6125","1573-0565"],"issn-type":[{"value":"0885-6125","type":"print"},{"value":"1573-0565","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,5,21]]},"assertion":[{"value":"18 July 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 April 2025","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 April 2025","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 May 2025","order":4,"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":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Not applicable.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}}],"article-number":"149"}}