{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T19:08:31Z","timestamp":1757617711473,"version":"3.44.0"},"publisher-location":"Cham","reference-count":31,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031863691"},{"type":"electronic","value":"9783031863707"}],"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\/978-3-031-86370-7_12","type":"book-chapter","created":{"date-parts":[[2025,4,4]],"date-time":"2025-04-04T07:37:51Z","timestamp":1743752271000},"page":"191-208","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Reinforcement Learning Algorithms with\u00a0Graph Convolution Networks for\u00a0Traffic Signal Control"],"prefix":"10.1007","author":[{"given":"Shreya","family":"Salmalge","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shalabh","family":"Bhatnagar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,4,3]]},"reference":[{"key":"12_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.: Adaptive traffic signal control with actor-critic methods in a real-world traffic network with different traffic disruption events. Transp. Res. Part C: Emerg. Technol. 85, 732\u2013752 (2017)","journal-title":"Transp. Res. Part C: Emerg. Technol."},{"issue":"11","key":"12_CR2","doi-asserted-by":"publisher","first-page":"2471","DOI":"10.1016\/j.automatica.2009.07.008","volume":"45","author":"S Bhatnagar","year":"2009","unstructured":"Bhatnagar, S., Sutton, R.S., Ghavamzadeh, M., Lee, M.: Natural actor-critic algorithms. Automatica 45(11), 2471\u20132482 (2009)","journal-title":"Automatica"},{"key":"12_CR3","doi-asserted-by":"crossref","unstructured":"Chen, C., et al.: Toward a thousand lights: decentralized deep reinforcement learning for large-scale traffic signal control. In: AAAI Conference on Artificial Intelligence (2020)","DOI":"10.1609\/aaai.v34i04.5744"},{"key":"12_CR4","doi-asserted-by":"crossref","unstructured":"Gammelli, D., Yang, K., Harrison, J., Rodrigues, F., Pereira, F.C., Pavone, M.: Graph neural network reinforcement learning for autonomous mobility-on-demand systems. In: 2021 60th IEEE Conference on Decision and Control (CDC), pp. 2996\u20133003 (2021)","DOI":"10.1109\/CDC45484.2021.9683135"},{"key":"12_CR5","doi-asserted-by":"publisher","first-page":"117","DOI":"10.1080\/15472450490435340","volume":"8","author":"M Girianna","year":"2004","unstructured":"Girianna, M., Benekohal, R.F.: Using genetic algorithms to design signal coordination for oversaturated networks. J. Intell. Transp. Syst. - J INTELL TRANSPORT SYST 8, 117\u2013129 (2004)","journal-title":"J. Intell. Transp. Syst. - J INTELL TRANSPORT SYST"},{"key":"12_CR6","doi-asserted-by":"crossref","unstructured":"Guo, Y., Wu, Q., She, H.: A routing optimization policy using graph convolution deep reinforcement learning. In: 2023 IEEE\/CIC International Conference on Communications in China (ICCC), pp. 1\u20136 (2023)","DOI":"10.1109\/ICCC57788.2023.10233329"},{"key":"12_CR7","unstructured":"Hegeman, T., Iosup, A.: Survey of graph analysis applications. CoRR abs\/1807.00382 (2018)"},{"key":"12_CR8","doi-asserted-by":"crossref","unstructured":"Houidi, O., Bakri, S., Zeghlache, D.: Multi-agent graph convolutional reinforcement learning for intelligent load balancing. In: NOMS 2022-2022 IEEE\/IFIP Network Operations and Management Symposium, pp. 1\u20136 (2022)","DOI":"10.1109\/NOMS54207.2022.9789872"},{"key":"12_CR9","doi-asserted-by":"publisher","first-page":"108497","DOI":"10.1016\/j.asoc.2022.108497","volume":"119","author":"G Kim","year":"2022","unstructured":"Kim, G., Sohn, K.: Area-wide traffic signal control based on a deep graph Q-network (DGQN) trained in an asynchronous manner. Appl. Soft Comput. 119, 108497 (2022)","journal-title":"Appl. Soft Comput."},{"key":"12_CR10","unstructured":"Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. CoRR, abs\/1609.02907 (2016)"},{"key":"12_CR11","doi-asserted-by":"crossref","unstructured":"Li, C., Ma, X., Xia, L., Zhao, Q., Yang, J.: Fairness control of traffic light via deep reinforcement learning. In: 2020 IEEE 16th International Conference on Automation Science and Engineering (CASE), pp. 652\u2013658 (2020)","DOI":"10.1109\/CASE48305.2020.9216899"},{"key":"12_CR12","doi-asserted-by":"crossref","unstructured":"Li, S.: Multi-agent deep deterministic policy gradient for traffic signal control on urban road network. In: 2020 IEEE International Conference on Advances in Electrical Engineering and Computer Applications( AEECA), pp. 896\u2013900 (2020)","DOI":"10.1109\/AEECA49918.2020.9213523"},{"issue":"8","key":"12_CR13","doi-asserted-by":"publisher","first-page":"11789","DOI":"10.1109\/TITS.2021.3107258","volume":"23","author":"D Ma","year":"2022","unstructured":"Ma, D., Zhou, B., Song, X., Dai, H.: A deep reinforcement learning approach to traffic signal control with temporal traffic pattern mining. IEEE Trans. Intell. Transp. Syst. 23(8), 11789\u201311800 (2022)","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"12_CR14","doi-asserted-by":"crossref","unstructured":"Mei, H., Lei, X., Da, L., Shi, B., Wei, H.: LibSignal: an open library for traffic signal control. Mach. Learn., 1\u201337 (2023)","DOI":"10.1007\/s10994-023-06412-y"},{"key":"12_CR15","unstructured":"Mnih, V., et al.: Asynchronous methods for deep reinforcement learning. In: International Conference on Machine Learning (2016)"},{"key":"12_CR16","unstructured":"Mnih, V., et al.: Playing Atari with deep reinforcement learning. CoRR, abs\/1312.5602 (2013)"},{"key":"12_CR17","doi-asserted-by":"crossref","unstructured":"Nishi, T., Otaki, K., Hayakawa, K., Yoshimura, T.: Traffic signal control based on reinforcement learning with graph convolutional neural nets. In: 2018 21st International Conference on Intelligent Transportation Systems (ITSC), pp. 877\u2013883 (2018)","DOI":"10.1109\/ITSC.2018.8569301"},{"key":"12_CR18","unstructured":"Oroojlooy, A., Nazari, M., Hajinezhad, D., Silva, J.: AttendLight: universal attention-based reinforcement learning model for traffic signal control (2020)"},{"key":"12_CR19","doi-asserted-by":"publisher","first-page":"401","DOI":"10.1016\/j.ins.2021.07.007","volume":"578","author":"H Peng","year":"2021","unstructured":"Peng, H., et al.: Dynamic graph convolutional network for long-term traffic flow prediction with reinforcement learning. Inf. Sci. 578, 401\u2013416 (2021)","journal-title":"Inf. Sci."},{"key":"12_CR20","doi-asserted-by":"crossref","unstructured":"Prabuchandran, K.J., AN, H.K., Bhatnagar, S.: Multi-agent reinforcement learning for traffic signal control. In: 17th International IEEE Conference on Intelligent Transportation Systems (ITSC), pp. 2529\u20132534 (2014)","DOI":"10.1109\/ITSC.2014.6958095"},{"issue":"2","key":"12_CR21","doi-asserted-by":"publisher","first-page":"412","DOI":"10.1109\/TITS.2010.2091408","volume":"12","author":"LA Prashanth","year":"2011","unstructured":"Prashanth, L.A., Bhatnagar, S.: Reinforcement learning with function approximation for traffic signal control. IEEE Trans. Intell. Transp. Syst. 12(2), 412\u2013421 (2011)","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"issue":"9","key":"12_CR22","doi-asserted-by":"publisher","first-page":"3865","DOI":"10.1109\/TVT.2012.2209904","volume":"61","author":"LA Prashanth","year":"2012","unstructured":"Prashanth, L.A., 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."},{"key":"12_CR23","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1287\/trsc.31.1.5","volume":"31","author":"S Sen","year":"1997","unstructured":"Sen, S., Head, K.L.: Controlled optimization of phases at an intersection. Transp. Sci. 31, 5\u201317 (1997)","journal-title":"Transp. Sci."},{"key":"12_CR24","doi-asserted-by":"crossref","unstructured":"ul\u00a0Asar, A., Ullah, M.S., Ahmed, J., ul\u00a0Hasnain, R.: Traffic responsive signal timing plan generation based on neural network. In: 2008 IEEE International Conference on Automation Science and Engineering, pp. 833\u2013838 (2008)","DOI":"10.1109\/COASE.2008.4626427"},{"key":"12_CR25","first-page":"279","volume":"8","author":"C Watkins","year":"1992","unstructured":"Watkins, C., Dayan, P.: Technical note: Q-learning. Mach. Learn. 8, 279\u2013292 (1992)","journal-title":"Mach. Learn."},{"key":"12_CR26","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, KDD 2019, pp. 1290-1298, New York. Association for Computing Machinery (2019)","DOI":"10.1145\/3292500.3330949"},{"key":"12_CR27","doi-asserted-by":"crossref","unstructured":"Wei, H., et al.: CoLight: learning network-level cooperation for traffic signal control. In: Proceedings of the 28th ACM International Conference on Information and Knowledge Management, CIKM 2019. ACM (2019)","DOI":"10.1145\/3357384.3357902"},{"key":"12_CR28","doi-asserted-by":"crossref","unstructured":"Xiangyun, Z., Lijun, W., Zhiyuan, L., Yulin, J.: Deep reinforcement learning with graph convolutional networks for load balancing in SDN-based data center networks. In: 2021 18th International Computer Conference on Wavelet Active Media Technology and Information Processing (ICCWAMTIP), pp. 344\u2013352 (2021)","DOI":"10.1109\/ICCWAMTIP53232.2021.9674074"},{"key":"12_CR29","doi-asserted-by":"publisher","first-page":"104855","DOI":"10.1016\/j.knosys.2019.07.026","volume":"183","author":"S Yang","year":"2019","unstructured":"Yang, S., Yang, B., Wong, H.-S., Kang, Z.: Cooperative traffic signal control using multi-step return and off-policy asynchronous advantage actor-critic graph algorithm. Knowl.-Based Syst. 183, 104855 (2019)","journal-title":"Knowl.-Based Syst."},{"key":"12_CR30","unstructured":"Yao, L., Mao, C., Luo, Y.: Graph convolutional networks for text classification. CoRR, abs\/1809.05679 (2018)"},{"issue":"4","key":"12_CR31","doi-asserted-by":"publisher","first-page":"263","DOI":"10.1016\/j.trc.2006.08.002","volume":"14","author":"X-H Yu","year":"2006","unstructured":"Yu, X.-H., Recker, W.W.: Stochastic adaptive control model for traffic signal systems. Transp. Res. Part C: Emerg. Technol. 14(4), 263\u2013282 (2006)","journal-title":"Transp. Res. Part C: Emerg. Technol."}],"container-title":["Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering","Intelligent Transport Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-86370-7_12","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,6]],"date-time":"2025-09-06T08:44:49Z","timestamp":1757148289000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-86370-7_12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031863691","9783031863707"],"references-count":31,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-86370-7_12","relation":{},"ISSN":["1867-8211","1867-822X"],"issn-type":[{"type":"print","value":"1867-8211"},{"type":"electronic","value":"1867-822X"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"3 April 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"INTSYS","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Transport Systems","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Pisa","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","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":"5 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":"8","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"intsys2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}