{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T06:40:54Z","timestamp":1743057654611,"version":"3.40.3"},"publisher-location":"Cham","reference-count":28,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783031229527"},{"type":"electronic","value":"9783031229534"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"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":[[2022]]},"DOI":"10.1007\/978-3-031-22953-4_6","type":"book-chapter","created":{"date-parts":[[2023,1,23]],"date-time":"2023-01-23T17:35:40Z","timestamp":1674495340000},"page":"122-142","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Co-operative Multi-agent Twin Delayed DDPG for\u00a0Robust Phase Duration Optimization of\u00a0Large Road Networks"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9452-3798","authenticated-orcid":false,"given":"Priya","family":"Shanmugasundaram","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7644-3914","authenticated-orcid":false,"given":"Shalabh","family":"Bhatnagar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,1,20]]},"reference":[{"key":"6_CR1","doi-asserted-by":"crossref","unstructured":"Abdulhai, B., Pringle, R., Karakoulas, G.J.: Reinforcement learning for true adaptive traffic signal control. J. Transp. Eng. 129(3) (2003)","DOI":"10.1061\/(ASCE)0733-947X(2003)129:3(278)"},{"key":"6_CR2","unstructured":"Ackermann, J., Gabler, V., Osa, T., Sugiyama, M.: Reducing overestimation bias in multi-agent domains using double centralized critics. arXiv preprint arXiv:1910.01465 (2019)"},{"key":"6_CR3","doi-asserted-by":"publisher","unstructured":"Balaji, P., Srinivasan, D.: Type-2 Fuzzy Logic based urban traffic management. Eng. Appl. Artif. Intell. 24(1), 12\u201322 (2011). https:\/\/doi.org\/10.1016\/j.engappai.2010.08.007. https:\/\/www.sciencedirect.com\/science\/article\/pii\/S0952197610001624","DOI":"10.1016\/j.engappai.2010.08.007"},{"key":"6_CR4","doi-asserted-by":"crossref","unstructured":"Bellman, R.: A Markovian decision process. J. Math. Mech. 679\u2013684 (1957)","DOI":"10.1512\/iumj.1957.6.56038"},{"issue":"3","key":"6_CR5","doi-asserted-by":"publisher","first-page":"1086","DOI":"10.1109\/TITS.2019.2901791","volume":"21","author":"T Chu","year":"2019","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 (2019)","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"issue":"6","key":"6_CR6","doi-asserted-by":"publisher","first-page":"870","DOI":"10.1287\/opre.12.6.870","volume":"12","author":"MC Dunne","year":"1964","unstructured":"Dunne, M.C., Potts, R.B.: Algorithm for traffic control. Oper. Res. 12(6), 870\u2013881 (1964)","journal-title":"Oper. Res."},{"issue":"6","key":"6_CR7","doi-asserted-by":"publisher","first-page":"815","DOI":"10.1287\/opre.12.6.815","volume":"12","author":"DC Gazis","year":"1964","unstructured":"Gazis, D.C.: Optimum control of a system of oversaturated intersections. Oper. Res. 12(6), 815\u2013831 (1964)","journal-title":"Oper. Res."},{"key":"6_CR8","doi-asserted-by":"publisher","first-page":"40797","DOI":"10.1109\/ACCESS.2019.2907618","volume":"7","author":"H Ge","year":"2019","unstructured":"Ge, H., Song, Y., Wu, C., Ren, J., Tan, G.: Cooperative deep q-learning with q-value transfer for multi-intersection signal control. IEEE Access 7, 40797\u201340809 (2019)","journal-title":"IEEE Access"},{"key":"6_CR9","unstructured":"Genders, W., Razavi, S.: Using a deep reinforcement learning agent for traffic signal control. arXiv preprint arXiv:1611.01142 (2016)"},{"key":"6_CR10","unstructured":"Head, L., Mirchandani, P., Shelby, S.: The Rhodes prototype: a description and some results (1998)"},{"key":"6_CR11","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"6_CR12","doi-asserted-by":"publisher","unstructured":"Prabuchandran, K.J., Hemanth Kumar, A.N., Bhatnagar, S.: Multi-agent reinforcement learning for traffic signal control. In: 17th International IEEE Conference on Intelligent Transportation Systems (ITSC), pp. 2529\u20132534 (2014). https:\/\/doi.org\/10.1109\/ITSC.2014.6958095","DOI":"10.1109\/ITSC.2014.6958095"},{"issue":"9","key":"6_CR13","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). https:\/\/doi.org\/10.1109\/TVT.2012.2209904","journal-title":"IEEE Trans. Veh. Technol."},{"issue":"2","key":"6_CR14","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). https:\/\/doi.org\/10.1109\/TITS.2010.2091408","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"issue":"3","key":"6_CR15","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.Y.: Traffic signal timing via deep reinforcement learning. IEEE\/CAA J. Automatica Sinica 3(3), 247\u2013254 (2016)","journal-title":"IEEE\/CAA J. Automatica Sinica"},{"key":"6_CR16","unstructured":"Liang, X., Du, X., Wang, G., Han, Z.: Deep reinforcement learning for traffic light control in vehicular networks. arXiv preprint arXiv:1803.11115 (2018)"},{"key":"6_CR17","unstructured":"Lillicrap, T.P., et al.: Continuous control with deep reinforcement learning. arXiv preprint arXiv:1509.02971 (2015)"},{"key":"6_CR18","unstructured":"Lowe, R., Wu, Y.I., Tamar, A., Harb, J., Pieter Abbeel, O., Mordatch, I.: Multi-agent actor-critic for mixed cooperative-competitive environments. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"6_CR19","unstructured":"Lowrie, P.: Scats: Sydney co-ordinated adaptive traffic system: a traffic responsive method of controlling urban traffic (1990)"},{"key":"6_CR20","doi-asserted-by":"publisher","unstructured":"Mauro, V., Di Taranto, C.: Utopia. IFAC Proc. Volumes 23(2), 245\u2013252 (1990). https:\/\/doi.org\/10.1016\/S1474-6670(17)52678-6. https:\/\/www.sciencedirect.com\/science\/article\/pii\/S1474667017526786. iFAC\/IFIP\/IFORS Symposium on Control, Computers, Communications in Transportation, Paris, France, 19\u201321 September","DOI":"10.1016\/S1474-6670(17)52678-6"},{"key":"6_CR21","doi-asserted-by":"publisher","unstructured":"Prashanth, L.A., Bhatnagar, S.: Reinforcement learning with average cost for adaptive control of traffic lights at intersections. In: 2011 14th International IEEE Conference on Intelligent Transportation Systems (ITSC), pp. 1640\u20131645 (2011). https:\/\/doi.org\/10.1109\/ITSC.2011.6082823","DOI":"10.1109\/ITSC.2011.6082823"},{"key":"6_CR22","volume-title":"Markov Decision Processes: Discrete Stochastic Dynamic Programming","author":"ML Puterman","year":"2014","unstructured":"Puterman, M.L.: Markov Decision Processes: Discrete Stochastic Dynamic Programming. Wiley, Hoboken (2014)"},{"key":"6_CR23","doi-asserted-by":"publisher","first-page":"865","DOI":"10.1016\/j.sbspro.2012.09.802","volume":"54","author":"R Riccardo","year":"2012","unstructured":"Riccardo, R., Massimiliano, G.: An empirical analysis of vehicle time headways on rural two-lane two-way roads. Procedia Soc. Behav. Sci. 54, 865\u2013874 (2012)","journal-title":"Procedia Soc. Behav. Sci."},{"key":"6_CR24","doi-asserted-by":"crossref","unstructured":"Shanmugasundaram, P., Bhatnagar, S.: Robust traffic signal timing control using multiagent twin delayed deep deterministic policy gradients. In: ICAART (2), pp. 477\u2013485 (2022)","DOI":"10.5220\/0010889300003116"},{"key":"6_CR25","doi-asserted-by":"publisher","unstructured":"Shanmugasundaram, P., Sinha, A.: Intelligent traffic control using double deep q networks for time-varying traffic flows. In: 2021 8th International Conference on Signal Processing and Integrated Networks (SPIN), pp. 64\u201369 (2021). https:\/\/doi.org\/10.1109\/SPIN52536.2021.9565961","DOI":"10.1109\/SPIN52536.2021.9565961"},{"issue":"4","key":"6_CR26","doi-asserted-by":"publisher","first-page":"289","DOI":"10.1016\/0191-2615(79)90021-3","volume":"13","author":"M Smith","year":"1979","unstructured":"Smith, M.: Traffic control and route-choice; a simple example. Transp. Res. Part B: Methodol. 13(4), 289\u2013294 (1979)","journal-title":"Transp. Res. Part B: Methodol."},{"key":"6_CR27","unstructured":"Tampuu, A., et al.: Multiagent cooperation and competition with deep reinforcement learning. CoRR abs\/1511.08779 (2015). http:\/\/arxiv.org\/abs\/1511.08779"},{"issue":"3","key":"6_CR28","doi-asserted-by":"publisher","first-page":"279","DOI":"10.1007\/BF00992698","volume":"8","author":"CJ Watkins","year":"1992","unstructured":"Watkins, C.J., Dayan, P.: Q-learning. Mach. Learn. 8(3), 279\u2013292 (1992)","journal-title":"Mach. Learn."}],"container-title":["Lecture Notes in Computer Science","Agents and Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-22953-4_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,23]],"date-time":"2023-01-23T17:39:07Z","timestamp":1674495547000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-22953-4_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031229527","9783031229534"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-22953-4_6","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"20 January 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICAART","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Agents and Artificial Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"3 February 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 February 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icaart2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.icaart.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":"PRIMORIS","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"302","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":"81","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":"114","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":"27% - 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","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":"4","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)"}}]}}