{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,28]],"date-time":"2026-03-28T01:59:26Z","timestamp":1774663166465,"version":"3.50.1"},"publisher-location":"Singapore","reference-count":14,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819698936","type":"print"},{"value":"9789819698943","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-981-96-9894-3_7","type":"book-chapter","created":{"date-parts":[[2025,7,25]],"date-time":"2025-07-25T19:57:19Z","timestamp":1753473439000},"page":"74-84","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["HMLight: Hierarchical Multi-Agent Deep Reinforcement Learning with Long-Short-Term Planning in Traffic Signal Control"],"prefix":"10.1007","author":[{"given":"Nan","family":"He","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nianwen","family":"Ning","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yi","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,7,26]]},"reference":[{"key":"7_CR1","doi-asserted-by":"crossref","unstructured":"Wei, H., et al.: Presslight: Learning max pressure control to coordinate traffic signals in arterial network. In: Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp. 1290\u20131298 (2019)","DOI":"10.1145\/3292500.3330949"},{"key":"7_CR2","doi-asserted-by":"crossref","unstructured":"Zheng, G., et al.: Learning phase competition for traffic signal control. In: Proceedings of the 28th ACM International Conference on Information and Knowledge Management, pp. 1963\u20131972 (2019)","DOI":"10.1145\/3357384.3357900"},{"key":"7_CR3","unstructured":"Casas, N.: Deep deterministic policy gradient for urban traffic light control. arXiv preprint arXiv:1703.09035 (2017)"},{"issue":"7","key":"7_CR4","doi-asserted-by":"publisher","first-page":"417","DOI":"10.1049\/iet-its.2017.0153","volume":"11","author":"SS Mousavi","year":"2017","unstructured":"Mousavi, S.S., Schukat, M., Howley, E.: Traffic light control using deep policy-gradient and value-function-based reinforcement learning. IET Intell. Transp. Syst. 11(7), 417\u2013423 (2017)","journal-title":"IET Intell. Transp. Syst."},{"key":"7_CR5","unstructured":"Van der Pol, E., Oliehoek, F.A.: 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 (2016)"},{"key":"7_CR6","doi-asserted-by":"crossref","unstructured":"Kuyer, L., Whiteson, S., Bakker, B., Vlassis, N.: Multiagent reinforcement learning for urban traffic control using coordination graphs. In: Machine Learning and Knowledge Discovery in Databases: European Conference, ECML PKDD 2008, Antwerp, Belgium, September 15\u201319, 2008, Proceedings, Part I, pp. 656\u2013671 (2008)","DOI":"10.1007\/978-3-540-87479-9_61"},{"key":"7_CR7","unstructured":"Wiering, M.A.: Multi-agent reinforcement learning for traffic light control. In: Machine Learning: Proceedings of the Seventeenth International Conference (ICML\u20192000), pp. 1151\u20131158 (2000)"},{"key":"7_CR8","doi-asserted-by":"crossref","unstructured":"Chu, T., Wang, J.: Traffic signal control by distributed reinforcement learning with min-sum communication. In: 2017 American Control Conference (ACC), pp. 5095\u20135100 (2017)","DOI":"10.23919\/ACC.2017.7963745"},{"issue":"3","key":"7_CR9","doi-asserted-by":"publisher","first-page":"1140","DOI":"10.1109\/TITS.2013.2255286","volume":"14","author":"S El-Tantawy","year":"2013","unstructured":"El-Tantawy, S., Abdulhai, B., Abdelgawad, H.: Multiagent reinforcement learning for integrated network of adaptive traffic signal controllers (MARLIN-ATSC): Methodology and large-scale application on downtown Toronto. IEEE Trans. Intell. Transp. Syst. 14(3), 1140\u20131150 (2013)","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"7_CR10","doi-asserted-by":"publisher","first-page":"487","DOI":"10.1016\/j.trc.2014.12.009","volume":"58","author":"F Zhu","year":"2015","unstructured":"Zhu, F., Aziz, H.M.A., Qian, X., Ukkusuri, S.V.: A junction-tree based learning algorithm to optimize network wide traffic control: A coordinated multi-agent framework. Transp. Res. Part C Emerg. Technol. 58, 487\u2013501 (2015)","journal-title":"Transp. Res. Part C Emerg. Technol."},{"key":"7_CR11","first-page":"3682","volume":"29","author":"TD Kulkarni","year":"2016","unstructured":"Kulkarni, T.D., Narasimhan, K., Saeedi, A., Tenenbaum, J.: Hierarchical deep reinforcement learning: Integrating temporal abstraction and intrinsic motivation. Adv. Neural Inf. Proces. Syst. 29, 3682\u20133690 (2016)","journal-title":"Adv. Neural Inf. Proces. Syst."},{"issue":"1","key":"7_CR12","first-page":"669","volume":"35","author":"B Xu","year":"2021","unstructured":"Xu, B., Wang, Y., Wang, Z., Jia, H., Lu, Z.: Hierarchically and cooperatively learning traffic signal control. Proc. AAAI Conf. Artif. Intell. 35(1), 669\u2013677 (2021)","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"issue":"04","key":"7_CR13","first-page":"3414","volume":"34","author":"C Chen","year":"2020","unstructured":"Chen, C., Wei, H., Xu, N., Zheng, G., Yang, M.: Toward a thousand lights: Decentralized deep reinforcement learning for large-scale traffic signal control. Proc. AAAI Conf. Artif. Intell. 34(04), 3414\u20133421 (2020)","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"7_CR14","unstructured":"S.C. Lobo, S. Neumeier, E.M. Fernandez, and C. Facchi. InTAS\u2013the ingolstadt traffic scenario for SUMO. arXiv preprint arXiv:2011.11995 (2020)"}],"container-title":["Lecture Notes in Computer Science","Advanced Intelligent Computing Technology and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-9894-3_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,28]],"date-time":"2026-03-28T01:37:39Z","timestamp":1774661859000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-9894-3_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819698936","9789819698943"],"references-count":14,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-9894-3_7","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"26 July 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Ningbo","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 July 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 July 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icic2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.ic-icc.cn\/icg\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}