{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T23:54:14Z","timestamp":1743033254138,"version":"3.40.3"},"publisher-location":"Cham","reference-count":23,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030858988"},{"type":"electronic","value":"9783030858995"}],"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\/978-3-030-85899-5_29","type":"book-chapter","created":{"date-parts":[[2021,8,18]],"date-time":"2021-08-18T10:06:38Z","timestamp":1629281198000},"page":"399-413","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Learning Cooperative Max-Pressure Control by Leveraging Downstream Intersections Information for Traffic Signal Control"],"prefix":"10.1007","author":[{"given":"Yuquan","family":"Peng","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lin","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qing","family":"Xie","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaohui","family":"Tao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,8,19]]},"reference":[{"key":"29_CR1","unstructured":"Webster, F.: Traffic signals. Road research technical paper 56 (1966)"},{"key":"29_CR2","unstructured":"Roess, R.P., Prassas, E.S., McShane, W.R.: Traffic Engineering. Pearson\/Prentice Hall (2004)"},{"key":"29_CR3","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.: Max pressure control of a network of signalized intersections. Transp. Res. Part C Emerging Technol. 36, 177\u2013195 (2013)","journal-title":"Transp. Res. Part C Emerging Technol."},{"issue":"4","key":"29_CR4","doi-asserted-by":"publisher","first-page":"373","DOI":"10.1057\/jors.1963.61","volume":"14","author":"AJ Miller","year":"1963","unstructured":"Miller, A.J.: Settings for fixed-cycle traffic signals. J. Oper. Res. Soc. 14(4), 373\u2013386 (1963)","journal-title":"J. Oper. Res. Soc."},{"key":"29_CR5","doi-asserted-by":"crossref","unstructured":"Yau, K.L.A., Qadir, J., Khoo, H.L., et al.: A survey on reinforcement learning models and algorithms for traffic signal control. ACM Comput. Surv. 50(3), 34:1\u201334:38 (2017)","DOI":"10.1145\/3068287"},{"key":"29_CR6","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) (2016)"},{"key":"29_CR7","doi-asserted-by":"crossref","unstructured":"Wei, H., Chen, C., Zheng, G., et al.: PressLight: learning max pressure control to coordinate traffic signals in arterial network. In: SIGKDD 2019, pp. 1290\u20131298 (2019)","DOI":"10.1145\/3292500.3330949"},{"key":"29_CR8","unstructured":"Zheng, G., Zang, X., Xu, N., et al.: Diagnosing reinforcement learning for traffic signal control. arXiv preprint arXiv:1905.04716 (2019)"},{"issue":"3","key":"29_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."},{"issue":"7","key":"29_CR10","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 Intel. Transp. Syst. 11(7), 417\u2013423 (2017)","journal-title":"IET Intel. Transp. Syst."},{"issue":"6","key":"29_CR11","doi-asserted-by":"publisher","first-page":"2687","DOI":"10.1109\/TCYB.2019.2904742","volume":"50","author":"T Tan","year":"2020","unstructured":"Tan, T., Bao, F., Deng, Y., 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."},{"issue":"3","key":"29_CR12","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\u00e0, 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."},{"key":"29_CR13","doi-asserted-by":"crossref","unstructured":"Chen, C., Wei, H., Xu, N., et al.: Toward a thousand lights: decentralized deep reinforcement learning for large-scale traffic signal control. In: AAAI 2020, pp. 3414\u20133421 (2020)","DOI":"10.1609\/aaai.v34i04.5744"},{"issue":"10","key":"29_CR14","doi-asserted-by":"publisher","first-page":"3710","DOI":"10.1109\/TITS.2018.2878001","volume":"20","author":"N Wu","year":"2019","unstructured":"Wu, N., Li, D., Xi, Y.: Distributed weighted balanced control of traffic signals for urban traffic congestion. IEEE Trans. Intell. Transp. Syst. 20(10), 3710\u20133720 (2019)","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"29_CR15","first-page":"1","volume":"2019","author":"S Hao","year":"2019","unstructured":"Hao, S., Yang, L., Ding, L., et al.: Distributed cooperative backpressure-based traffic light control method. J. Adv. Transp. 2019, 1\u201313 (2019)","journal-title":"J. Adv. Transp."},{"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., Kavukcuoglu, K., Silver, D., et al.: Human-level control through deep reinforcement learning. Nat. 518(7540), 529\u2013533 (2015)","journal-title":"Nat."},{"key":"29_CR17","unstructured":"Wiering, M.A.: Multi-agent reinforcement learning for traffic light control. In: ICML 2000, pp. 1151\u20131158 (2000)"},{"key":"29_CR18","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"656","DOI":"10.1007\/978-3-540-87479-9_61","volume-title":"Machine Learning and Knowledge Discovery in Databases","author":"L Kuyer","year":"2008","unstructured":"Kuyer, L., Whiteson, S., Bakker, B., Vlassis, N.: Multiagent reinforcement learning for urban traffic control using coordination graphs. In: Daelemans, W., Goethals, B., Morik, K. (eds.) ECML PKDD 2008. LNCS (LNAI), vol. 5211, pp. 656\u2013671. Springer, Heidelberg (2008). https:\/\/doi.org\/10.1007\/978-3-540-87479-9_61"},{"issue":"3\u20134","key":"29_CR19","first-page":"279","volume":"8","author":"CJ Watkins","year":"1992","unstructured":"Watkins, C.J., Dayan, P.: Q-learning. Mach. Learn. 8(3\u20134), 279\u2013292 (1992)","journal-title":"Mach. Learn."},{"key":"29_CR20","doi-asserted-by":"crossref","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)","DOI":"10.1109\/TITS.2010.2091408"},{"key":"29_CR21","doi-asserted-by":"crossref","unstructured":"Zhou, N., Du, J., Yao, X., et al.: A content search method for security topics in microblog based on deep reinforcement learning. World Wide Web 23(1), 75\u2013101 (2020)","DOI":"10.1007\/s11280-019-00697-7"},{"key":"29_CR22","doi-asserted-by":"crossref","unstructured":"Ren, C., An, L., Gu, Z., et al.: Rebalancing the car-sharing system with reinforcement learning. World Wide Web 23(4), 2491\u20132511 (2020)","DOI":"10.1007\/s11280-020-00804-z"},{"key":"29_CR23","unstructured":"Zhao, C., Hu, X., Wang, G.: PDLight: a deep reinforcement learning traffic light control algorithm with pressure and dynamic light duration. arXiv preprint arXiv:2009.13711 (2020)"}],"container-title":["Lecture Notes in Computer Science","Web and Big Data"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-85899-5_29","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,8,19]],"date-time":"2021-08-19T23:42:54Z","timestamp":1629416574000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-85899-5_29"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030858988","9783030858995"],"references-count":23,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-85899-5_29","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"19 August 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"APWeb-WAIM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Asia-Pacific Web (APWeb) and Web-Age Information Management (WAIM) Joint International Conference on Web and Big Data","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Guangzhou","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":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 August 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25 August 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"apwebwaim2021","order":10,"name":"conference_id","label":"Conference ID","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":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"184","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":"44","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":"24","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":"3.6","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":"6.38","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":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}