{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T20:07:31Z","timestamp":1775074051634,"version":"3.50.1"},"publisher-location":"Cham","reference-count":34,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030865139","type":"print"},{"value":"9783030865146","type":"electronic"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021]]},"DOI":"10.1007\/978-3-030-86514-6_29","type":"book-chapter","created":{"date-parts":[[2021,9,9]],"date-time":"2021-09-09T12:05:38Z","timestamp":1631189138000},"page":"470-485","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["Multi-agent Deep Reinforcement Learning with Spatio-Temporal Feature Fusion for Traffic Signal Control"],"prefix":"10.1007","author":[{"given":"Xin","family":"Du","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiahai","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Siyuan","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhiyue","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,9,10]]},"reference":[{"issue":"2\u20133","key":"29_CR1","doi-asserted-by":"publisher","first-page":"235","DOI":"10.1023\/A:1013689704352","volume":"47","author":"P Auer","year":"2002","unstructured":"Auer, P., Cesa-Bianchi, N., Fischer, P.: Finite-time analysis of the multiarmed bandit problem. Mach. Learn. 47(2\u20133), 235\u2013256 (2002). https:\/\/doi.org\/10.1023\/A:1013689704352","journal-title":"Mach. Learn."},{"key":"29_CR2","unstructured":"Bai, S., Kolter, J.Z., Koltun, V.: An empirical evaluation of generic convolutional and recurrent networks for sequence modeling. arXiv preprint arXiv:1803.01271 (2018)"},{"key":"29_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 2020, vol. 34, no. 4, pp. 3414\u20133421 (2020)","DOI":"10.1609\/aaai.v34i04.5744"},{"key":"29_CR4","doi-asserted-by":"crossref","unstructured":"Choe, C., Baek, S., Woon, B., Kong, S.H.: Deep Q learning with LSTM for traffic light control. In: 2018 24th Asia-Pacific Conference on Communications (APCC), pp. 331\u2013336 (2018)","DOI":"10.1109\/APCC.2018.8633520"},{"issue":"3","key":"29_CR5","doi-asserted-by":"publisher","first-page":"1086","DOI":"10.1109\/TITS.2019.2901791","volume":"21","author":"T Chu","year":"2020","unstructured":"Chu, T., Wang, J., Codec, L., Li, Z.: Multi-agent deep reinforcement learning for large-scale traffic signal control. IEEE Trans. Intell. Transp. Syst. 21(3), 1086\u20131095 (2020)","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"issue":"9","key":"29_CR6","doi-asserted-by":"publisher","first-page":"3272","DOI":"10.1109\/TITS.2018.2873790","volume":"20","author":"K Gao","year":"2019","unstructured":"Gao, K., et al.: Solving traffic signal scheduling problems in heterogeneous traffic network by using meta-heuristics. IEEE Trans. Intell. Transp. Syst. 20(9), 3272\u20133282 (2019)","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"29_CR7","doi-asserted-by":"crossref","unstructured":"Garg, D., Chli, M., Vogiatzis, G.: Deep reinforcement learning for autonomous traffic light control. In: 2018 3rd IEEE International Conference on Intelligent Transportation Engineering (ICITE), pp. 214\u2013218 (2018)","DOI":"10.1109\/ICITE.2018.8492537"},{"key":"29_CR8","doi-asserted-by":"publisher","first-page":"36","DOI":"10.1016\/j.cor.2014.10.001","volume":"55","author":"S Gottlich","year":"2015","unstructured":"Gottlich, S., Herty, M., Ziegler, U.: Modeling and optimizing traffic light settings in road networks. Comput. Oper. Res. 55, 36\u201351 (2015)","journal-title":"Comput. Oper. Res."},{"key":"29_CR9","doi-asserted-by":"publisher","unstructured":"Haydari, A., Yilmaz, Y.: Deep reinforcement learning for intelligent transportation systems: a survey. IEEE Trans. Intell. Transp. Syst., 1\u201322 (2020, in press). https:\/\/doi.org\/10.1109\/TITS.2020.3008612","DOI":"10.1109\/TITS.2020.3008612"},{"key":"29_CR10","unstructured":"Hsu, J.: Alibaba cloud launched \u2018ET City Brain 2.0\u2019 in Hangzhou (2018)"},{"key":"29_CR11","doi-asserted-by":"crossref","unstructured":"Hu, H.C., Smith, S.F., Goldstein, R.: Cooperative schedule-driven intersection control with connected and autonomous vehicles. In: IROS 2019, pp. 1668\u20131673 (2019)","DOI":"10.1109\/IROS40897.2019.8967975"},{"key":"29_CR12","doi-asserted-by":"crossref","unstructured":"Hu, H.C., Smith, S.F.: Learning model parameters for decentralized schedule-driven traffic control. In: ICAPS 2020, pp. 531\u2013539 (2020)","DOI":"10.1609\/icaps.v30i1.6749"},{"key":"29_CR13","unstructured":"Koonce, P., Rodegerdts, L.: Traffic signal timing manual. Technical report, United States. Federal Highway Administration (2008)"},{"issue":"3","key":"29_CR14","doi-asserted-by":"publisher","first-page":"247","DOI":"10.1109\/JAS.2016.7508798","volume":"3","author":"L Li","year":"2016","unstructured":"Li, L., Lv, Y., Wang, F.: Traffic signal timing via deep reinforcement learning. IEEE\/CAA J. Autom. Sin. 3(3), 247\u2013254 (2016)","journal-title":"IEEE\/CAA J. Autom. Sin."},{"issue":"2","key":"29_CR15","doi-asserted-by":"publisher","first-page":"1243","DOI":"10.1109\/TVT.2018.2890726","volume":"68","author":"X Liang","year":"2019","unstructured":"Liang, X., Du, X., Wang, G., Han, Z.: A deep reinforcement learning network for traffic light cycle control. IEEE Trans. Veh. Technol. 68(2), 1243\u20131253 (2019)","journal-title":"IEEE Trans. Veh. Technol."},{"issue":"7540","key":"29_CR16","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1038\/nature14236","volume":"518","author":"V Mnih","year":"2015","unstructured":"Mnih, V., et al.: Human-level control through deep reinforcement learning. Nature 518(7540), 529\u2013533 (2015)","journal-title":"Nature"},{"issue":"7","key":"29_CR17","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":"29_CR18","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, pp. 877\u2013883 (2018)","DOI":"10.1109\/ITSC.2018.8569301"},{"key":"29_CR19","unstructured":"Pol, E.V.D., Oliehoek, F.A.: Coordinated deep reinforcement learners for traffic light control. In: NeurIPS 2016 (2016)"},{"key":"29_CR20","unstructured":"Schaul, T., Quan, J., Antonoglou, I., Silver, D.: Prioritized experience replay. In: ICLR 2016 (2016)"},{"issue":"6","key":"29_CR21","doi-asserted-by":"publisher","first-page":"2687","DOI":"10.1109\/TCYB.2019.2904742","volume":"50","author":"T Tan","year":"2020","unstructured":"Tan, T., et al.: Cooperative deep reinforcement learning for large-scale traffic grid signal control. IEEE Trans. Cybern. 50(6), 2687\u20132700 (2020)","journal-title":"IEEE Trans. Cybern."},{"key":"29_CR22","series-title":"Complex Networks and Dynamic Systems","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1007\/978-1-4614-6243-9_2","volume-title":"Advances in Dynamic Network Modeling in Complex Transportation Systems","author":"P Varaiya","year":"2013","unstructured":"Varaiya, P.: The max-pressure controller for arbitrary networks of signalized intersections. In: Ukkusuri, S., Ozbay, K. (eds.) Advances in Dynamic Network Modeling in Complex Transportation Systems. Complex Networks and Dynamic Systems, vol. 2, pp. 27\u201366. Springer, New York (2013). https:\/\/doi.org\/10.1007\/978-1-4614-6243-9_2"},{"issue":"8","key":"29_CR23","doi-asserted-by":"publisher","first-page":"3152","DOI":"10.1109\/TITS.2019.2929020","volume":"21","author":"M Veres","year":"2020","unstructured":"Veres, M., Moussa, M.: Deep learning for intelligent transportation systems: A survey of emerging trends. IEEE Trans. Intell. Transp. Syst. 21(8), 3152\u20133168 (2020)","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"issue":"3","key":"29_CR24","first-page":"1086","volume":"21","author":"X Wang","year":"2020","unstructured":"Wang, X., Ke, L., Qiao, Z., Chai, X.: Large-scale traffic signal control using a novel multiagent reinforcement learning. IEEE Trans. Cybern. 21(3), 1086\u20131095 (2020)","journal-title":"IEEE Trans. Cybern."},{"key":"29_CR25","doi-asserted-by":"publisher","unstructured":"Wang, Y., et al.: STMARL: A spatio-temporal multi-agent reinforcement learning approach for cooperative traffic light control. IEEE Trans. Mob. Comput., 1\u201315 (2020, in press). https:\/\/doi.org\/10.1109\/TMC.2020.3033782","DOI":"10.1109\/TMC.2020.3033782"},{"key":"29_CR26","unstructured":"Wei, H., Zheng, G., Gayah, V., Li, Z.: A survey on traffic signal control methods. arXiv preprint arXiv:1904.08117 (2019)"},{"issue":"2","key":"29_CR27","doi-asserted-by":"publisher","first-page":"12","DOI":"10.1145\/3447556.3447565","volume":"22","author":"H Wei","year":"2020","unstructured":"Wei, H., Zheng, G., Gayah, V., Li, Z.: Recent advances in reinforcement learning for traffic signal control: A survey of models and evaluation. ACM SIGKDD Explor. Newsl. 22(2), 12\u201318 (2020)","journal-title":"ACM SIGKDD Explor. Newsl."},{"key":"29_CR28","doi-asserted-by":"crossref","unstructured":"Wei, H., Zheng, G., Yao, H., Li, Z.: IntelliLight: A reinforcement learning approach for intelligent traffic light control. In: KDD 2018, pp. 2496\u20132505 (2018)","DOI":"10.1145\/3219819.3220096"},{"key":"29_CR29","doi-asserted-by":"crossref","unstructured":"Wei, H., et al.: CoLight: Learning network-level cooperation for traffic signal control. In: CIKM 2019, pp. 1913\u20131922 (2019)","DOI":"10.1145\/3357384.3357902"},{"key":"29_CR30","doi-asserted-by":"crossref","unstructured":"Wei, H., et al.: PressLight: Learning max pressure control to coordinate traffic signals in arterial network. In: KDD 2019, pp. 1290\u20131298 (2019)","DOI":"10.1145\/3292500.3330949"},{"key":"29_CR31","doi-asserted-by":"publisher","unstructured":"Ye, J., Zhao, J., Ye, K., Xu, C.: How to build a graph-based deep learning architecture in traffic domain: A survey. IEEE Trans. Intell. Transp. Syst., 1\u201321 (2020, in press). https:\/\/doi.org\/10.1109\/TITS.2020.3043250","DOI":"10.1109\/TITS.2020.3043250"},{"key":"29_CR32","doi-asserted-by":"crossref","unstructured":"Zhang, H., et al.: CityFlow: A multi-agent reinforcement learning environment for large scale city traffic scenario. In: WWW 2019, pp. 3620\u20133624 (2019)","DOI":"10.1145\/3308558.3314139"},{"key":"29_CR33","unstructured":"Zheng, G., et al.: Diagnosing reinforcement learning for traffic signal control. arXiv preprint arXiv:1905.04716 (2019)"},{"key":"29_CR34","doi-asserted-by":"crossref","unstructured":"Zheng, G., et al.: Learning phase competition for traffic signal control. In: CIKM 2019, pp. 1963\u20131972 (2019)","DOI":"10.1145\/3357384.3357900"}],"container-title":["Lecture Notes in Computer Science","Machine Learning and Knowledge Discovery in Databases. Applied Data Science Track"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-86514-6_29","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,8]],"date-time":"2025-09-08T22:05:10Z","timestamp":1757369110000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-86514-6_29"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030865139","9783030865146"],"references-count":34,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-86514-6_29","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"10 September 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECML PKDD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Joint European Conference on Machine Learning and Knowledge Discovery in Databases","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Bilbao","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Spain","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 September 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 September 2021","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":"ecml2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/2021.ecmlpkdd.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"869","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"210","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"24% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3-4","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3-9","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"The conference was held online due to the COVID-19 pandemic.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}