{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T19:19:07Z","timestamp":1757618347742,"version":"3.44.0"},"publisher-location":"Singapore","reference-count":32,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819666058"},{"type":"electronic","value":"9789819666065"}],"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\/978-981-96-6606-5_16","type":"book-chapter","created":{"date-parts":[[2025,6,23]],"date-time":"2025-06-23T02:41:28Z","timestamp":1750646488000},"page":"227-242","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Agent Clustering and\u00a0Information Sharing Underlying MADRQN for\u00a0Traffic Light Cooperative Control"],"prefix":"10.1007","author":[{"given":"Haoran","family":"Cheng","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bo","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jie","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tongchun","family":"Du","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,6,24]]},"reference":[{"key":"16_CR1","doi-asserted-by":"publisher","first-page":"278","DOI":"10.1016\/j.trpro.2022.02.035","volume":"62","author":"K B\u00e1lint","year":"2022","unstructured":"B\u00e1lint, K., Tam\u00e1s, T., Tam\u00e1s, B.: Deep reinforcement learning based approach for traffic signal control. Transp. Res. Procedia 62, 278\u2013285 (2022)","journal-title":"Transp. Res. Procedia"},{"key":"16_CR2","doi-asserted-by":"crossref","unstructured":"Chiu, S.: Adaptive traffic signal control using fuzzy logic. In: Proceedings of the Intelligent Vehicles92 Symposium, pp. 98\u2013107. IEEE (1992)","DOI":"10.1109\/IVS.1992.252240"},{"issue":"2","key":"16_CR3","doi-asserted-by":"publisher","first-page":"182","DOI":"10.1109\/4235.996017","volume":"6","author":"K Deb","year":"2002","unstructured":"Deb, K., Pratap, A., Agarwal, S., Meyarivan, T.: A fast and elitist multiobjective genetic algorithm: NSGA-II. IEEE Trans. Evol. Comput. 6(2), 182\u2013197 (2002)","journal-title":"IEEE Trans. Evol. Comput."},{"issue":"3","key":"16_CR4","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":"16_CR5","doi-asserted-by":"crossref","unstructured":"Foerster, J., Farquhar, G., Afouras, T., Nardelli, N., Whiteson, S.: Counterfactual multi-agent policy gradients. In: Proceedings of the AAAI Conference on Artificial Intelligence. vol.\u00a032 (2018)","DOI":"10.1609\/aaai.v32i1.11794"},{"key":"16_CR6","doi-asserted-by":"crossref","unstructured":"Fritzke, B.: A growing neural gas network learns topologies. Adv. Neural Inf. Process. Syst. 7 (1994)","DOI":"10.1016\/0893-6080(94)90091-4"},{"key":"16_CR7","unstructured":"Genders, W., Razavi, S.: Using a deep reinforcement learning agent for traffic signal control. arXiv preprint arXiv:1611.01142 (2016)"},{"key":"16_CR8","doi-asserted-by":"crossref","unstructured":"Haddad, T.A., Hedjazi, D., Aouag, S.: A new deep reinforcement learning-based adaptive traffic light control approach for isolated intersection. In: 2022 5th International Symposium on Informatics and its Applications (ISIA), pp.\u00a01\u20136. IEEE (2022)","DOI":"10.1109\/ISIA55826.2022.9993598"},{"issue":"1","key":"16_CR9","doi-asserted-by":"publisher","first-page":"95","DOI":"10.1007\/s10489-023-05197-w","volume":"54","author":"J Huang","year":"2024","unstructured":"Huang, J., Tan, Q., Qi, R., Li, H.: RELight: a random ensemble reinforcement learning based method for traffic light control. Appl. Intell. 54(1), 95\u2013112 (2024)","journal-title":"Appl. Intell."},{"key":"16_CR10","unstructured":"Hunt, P., Robertson, D., Bretherton, R., Royle, M.C.: The scoot on-line traffic signal optimisation technique. Traffic Eng. Control 23(4) (1982)"},{"key":"16_CR11","unstructured":"Jiang, J., Lu, Z.: Learning attentional communication for multi-agent cooperation. Adv. Neural Inf. Process. Syst. 31 (2018)"},{"key":"16_CR12","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2023.110304","volume":"141","author":"L Kang","year":"2023","unstructured":"Kang, L., Huang, H., Lu, W., Liu, L.: A dueling deep q-network method for low-carbon traffic signal control. Appl. Soft Comput. 141, 110304 (2023)","journal-title":"Appl. Soft Comput."},{"issue":"10","key":"16_CR13","doi-asserted-by":"publisher","first-page":"8667","DOI":"10.1109\/TVT.2017.2702388","volume":"66","author":"W Liu","year":"2017","unstructured":"Liu, W., Qin, G., He, Y., Jiang, F.: Distributed cooperative reinforcement learning-based traffic signal control that integrates V2X networks\u2019 dynamic clustering. IEEE Trans. Veh. Technol. 66(10), 8667\u20138681 (2017)","journal-title":"IEEE Trans. Veh. Technol."},{"key":"16_CR14","unstructured":"Lowe, R., Wu, Y.I., Tamar, A., Harb, J., Pieter\u00a0Abbeel, O., Mordatch, I.: Multi-agent actor-critic for mixed cooperative-competitive environments. Adv. Neural Inf. Process. Syst. 30 (2017)"},{"key":"16_CR15","unstructured":"Luk, J.: Two traffic-responsive area traffic control methods: scat and scoot. Traffic Eng. Control 25(1) (1984)"},{"key":"16_CR16","unstructured":"Mingli, S., andHU Ming, C.E., Yue, Z., Wenjie, C., Mingsong, C., et\u00a0al.: Traffic light optimization control method for priority vehicle awareness. J. Softw. 32(8), 2425\u20132438 (2021)"},{"issue":"4","key":"16_CR17","doi-asserted-by":"publisher","first-page":"1459","DOI":"10.1109\/TVT.2013.2241460","volume":"62","author":"K Pandit","year":"2013","unstructured":"Pandit, K., Ghosal, D., Zhang, H.M., Chuah, C.N.: Adaptive traffic signal control with vehicular ad hoc networks. IEEE Trans. Veh. Technol. 62(4), 1459\u20131471 (2013)","journal-title":"IEEE Trans. Veh. Technol."},{"key":"16_CR18","unstructured":"Peng, P., et al.: Multiagent bidirectionally-coordinated nets: Emergence of human-level coordination in learning to play starcraft combat games. arXiv preprint arXiv:1703.10069 (2017)"},{"issue":"9","key":"16_CR19","doi-asserted-by":"publisher","first-page":"3865","DOI":"10.1109\/TVT.2012.2209904","volume":"61","author":"L Prashanth","year":"2012","unstructured":"Prashanth, L., Bhatnagar, S.: Threshold tuning using stochastic optimization for graded signal control. IEEE Trans. Veh. Technol. 61(9), 3865\u20133880 (2012)","journal-title":"IEEE Trans. Veh. Technol."},{"issue":"178","key":"16_CR20","first-page":"1","volume":"21","author":"T Rashid","year":"2020","unstructured":"Rashid, T., Samvelyan, M., De Witt, C.S., Farquhar, G., Foerster, J., Whiteson, S.: Monotonic value function factorisation for deep multi-agent reinforcement learning. J. Mach. Learn. Res. 21(178), 1\u201351 (2020)","journal-title":"J. Mach. Learn. Res."},{"key":"16_CR21","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.ins.2020.05.001","volume":"533","author":"B Richhariya","year":"2020","unstructured":"Richhariya, B., Tanveer, M., Initiative, A., et al.: Least squares projection twin support vector clustering (LSPTSVC). Inf. Sci. 533, 1\u201323 (2020)","journal-title":"Inf. Sci."},{"key":"16_CR22","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)"},{"key":"16_CR23","unstructured":"Son, K., Kim, D., Kang, W.J., Hostallero, D.E., Yi, Y.: QTRAN: learning to factorize with transformation for cooperative multi-agent reinforcement learning. In: International Conference on Machine Learning, pp. 5887\u20135896. PMLR (2019)"},{"key":"16_CR24","unstructured":"Storn, R., Price, K.V., Lampinen, J.: Differential evolution-a practical approach to global optimization (2005)"},{"key":"16_CR25","unstructured":"Su, H., Zhong, Y.D., Dey, B., Chakraborty, A.: A decentralized reinforcement learning framework for efficient passage of emergency vehicles. arXiv preprint arXiv:2111.00278 (2021)"},{"key":"16_CR26","unstructured":"Sukhbaatar, S., Fergus, R., et\u00a0al.: Learning multiagent communication with backpropagation. Adv. Neural Inf. Process. Syst. 29 (2016)"},{"key":"16_CR27","unstructured":"Sunehag, P., et\u00a0al.: Value-decomposition networks for cooperative multi-agent learning. arXiv preprint arXiv:1706.05296 (2017)"},{"issue":"6","key":"16_CR28","doi-asserted-by":"publisher","first-page":"1820","DOI":"10.1109\/TCSS.2021.3122828","volume":"9","author":"M Tanveer","year":"2021","unstructured":"Tanveer, M., Tabish, M., Jangir, J.: Sparse pinball twin bounded support vector clustering. IEEE Trans. Comput. Soc. Syst. 9(6), 1820\u20131829 (2021)","journal-title":"IEEE Trans. Comput. Soc. Syst."},{"key":"16_CR29","doi-asserted-by":"crossref","unstructured":"Tigga, A., Hota, L., Patel, S., Kumar, A.: A deep q-learning-based adaptive traffic light control system for urban safety. In: 2022 4th International Conference on Advances in Computing, Communication Control and Networking (ICAC3N), pp. 2430\u20132435. IEEE (2022)","DOI":"10.1109\/ICAC3N56670.2022.10074123"},{"key":"16_CR30","doi-asserted-by":"publisher","first-page":"343","DOI":"10.1016\/j.aej.2022.12.028","volume":"67","author":"I Tunc","year":"2023","unstructured":"Tunc, I., Soylemez, M.T.: Fuzzy logic and deep q learning based control for traffic lights. Alex. Eng. J. 67, 343\u2013359 (2023)","journal-title":"Alex. Eng. J."},{"issue":"6","key":"16_CR31","doi-asserted-by":"publisher","first-page":"6248","DOI":"10.1007\/s10489-022-03208-w","volume":"53","author":"L Yan","year":"2023","unstructured":"Yan, L., et al.: Graph cooperation deep reinforcement learning for ecological urban traffic signal control. Appl. Intell. 53(6), 6248\u20136265 (2023)","journal-title":"Appl. Intell."},{"key":"16_CR32","doi-asserted-by":"publisher","first-page":"243","DOI":"10.1016\/j.inffus.2023.02.009","volume":"94","author":"S Yang","year":"2023","unstructured":"Yang, S., Yang, B., Zeng, Z., Kang, Z.: Causal inference multi-agent reinforcement learning for traffic signal control. Inf. Fusion 94, 243\u2013256 (2023)","journal-title":"Inf. Fusion"}],"container-title":["Lecture Notes in Computer Science","Neural Information Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-6606-5_16","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,6]],"date-time":"2025-09-06T21:40:58Z","timestamp":1757194858000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-6606-5_16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819666058","9789819666065"],"references-count":32,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-6606-5_16","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"24 June 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"All authors declare that they have no competing financial interests or personal relationships that could influence the work reported in this paper.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"value":"ICONIP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Neural Information Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Auckland","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"New Zealand","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6 December 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"31","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iconip2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/iconip2024.org","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}