{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T03:03:52Z","timestamp":1778123032213,"version":"3.51.4"},"reference-count":36,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2023,2,2]],"date-time":"2023-02-02T00:00:00Z","timestamp":1675296000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,2,2]],"date-time":"2023-02-02T00:00:00Z","timestamp":1675296000000},"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":["Int. J. ITS Res."],"published-print":{"date-parts":[[2023,4]]},"DOI":"10.1007\/s13177-023-00346-4","type":"journal-article","created":{"date-parts":[[2023,2,2]],"date-time":"2023-02-02T11:47:43Z","timestamp":1675338463000},"page":"192-206","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":20,"title":["Deep Reinforcement Q-Learning for Intelligent Traffic Signal Control with Partial Detection"],"prefix":"10.1007","volume":"21","author":[{"given":"Romain","family":"Ducrocq","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0309-8942","authenticated-orcid":false,"given":"Nadir","family":"Farhi","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,2,2]]},"reference":[{"key":"346_CR1","first-page":"1","volume":"5","author":"J Alam","year":"2015","unstructured":"Alam, J., ey, M.K.: Design and analysis of a two stage traffic light system using fuzzy logic. J. Inf. Technol. Softw. Eng. 5, 1\u20139 (2015)","journal-title":"J. Inf. Technol. Softw. Eng."},{"key":"346_CR2","unstructured":"Alemzadeh, S., Moslemi, R., Sharma, R., Mesbahi, M.: Adaptive traffic control with deep reinforcement learning towards state-of-the-art and beyond. arXiv:2007.10960 (2020)"},{"key":"346_CR3","doi-asserted-by":"publisher","unstructured":"Chen, C., Wei, H., Xu, N., Zheng, G., Yang, M., Xiong, Y., Xu, K., Li, Z.: Toward a thousand lights: decentralized deep reinforcement learning for large-scale traffic signal control. In: Proceedings of the AAAI conference on artificial intelligence, vol. 34(04), pp. 3414\u20133421. https:\/\/doi.org\/10.1609\/aaai.v34i04.5744. https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/5744 (2020)","DOI":"10.1609\/aaai.v34i04.5744"},{"key":"346_CR4","doi-asserted-by":"crossref","unstructured":"Codec\u00e0, L., Frank, R., Engel, T.: Luxembourg sumo traffic (lust) scenario: 24 hours of mobility for vehicular networking research. In: 2015 IEEE vehicular networking conference (VNC), pp. 1\u20138 (2015)","DOI":"10.1109\/VNC.2015.7385539"},{"key":"346_CR5","unstructured":"Gao, J., Shen, Y., Liu, J., Ito, M., Shiratori, N.: Adaptive traffic signal control deep reinforcement learning algorithm with experience replay and target network. arXiv:1705.02755 (2017)"},{"key":"346_CR6","doi-asserted-by":"crossref","unstructured":"Genders, W., Razavi, S.N.: Evaluating reinforcement learning state representations for adaptive traffic signal control. In: ANT\/SEIT (2018)","DOI":"10.1016\/j.procs.2018.04.008"},{"key":"346_CR7","unstructured":"Genders, W., Razavi, S.N.: An open-source framework for adaptive traffic signal control. arXiv:1909.00395 (2019)"},{"key":"346_CR8","doi-asserted-by":"crossref","unstructured":"Gershenson, C.: Self-organizing traffic lights. Complex Syst.:16 (2005)","DOI":"10.25088\/ComplexSystems.16.1.29"},{"key":"346_CR9","unstructured":"Hasselt, H.V., Guez, A., Silver, D.: Deep reinforcement learning with double q-learning. arXiv:1509.06461 (2016)"},{"key":"346_CR10","doi-asserted-by":"crossref","unstructured":"Hessel, M., Modayil, J., Hasselt, H.V., Schaul, T., Ostrovski, G., Dabney, W., Horgan, D., Piot, B., Azar, M.G., Silver, D.: Rainbow: Combining improvements in deep reinforcement learning. In: AAAI (2018)","DOI":"10.1609\/aaai.v32i1.11796"},{"key":"346_CR11","unstructured":"Kheterpal, N., Parvate, K., Wu, C., Kreidieh, A., Vinitsky, E., Bayen, A.M.: Flow: deep reinforcement learning for control in sumo (2018)"},{"key":"346_CR12","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. CoRR arXiv:1412.6980(2015)"},{"key":"346_CR13","unstructured":"Krajzewicz, D., Erdmann, J., Behrisch, M., Bieker, L.: Recent development and applications of sumo \u2013 simulation of urban mobility (2012)"},{"key":"346_CR14","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1145\/3065386","volume":"60","author":"A Krizhevsky","year":"2012","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. Commun. ACM 60, 84\u201390 (2012)","journal-title":"Commun. ACM"},{"key":"346_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.: Traffic signal timing via deep reinforcement learning. IEEE\/CAA J. Autom. Sinica 3, 247\u2013254 (2016)","journal-title":"IEEE\/CAA J. Autom. Sinica"},{"key":"346_CR16","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, 1243\u20131253 (2019)","journal-title":"IEEE Trans. Veh. Technol."},{"key":"346_CR17","unstructured":"Lillicrap, T.P., Hunt, J.J., Pritzel, A., Heess, N.M.O., Erez, T., Tassa, Y., Silver, D., Wierstra, D.: Continuous control with deep reinforcement learning. CoRR arXiv:1509.02971 (2016)"},{"key":"346_CR18","unstructured":"Mnih, V., Kavukcuoglu, K., Silver, D., Graves, A., Antonoglou, I., Wierstra, D., Riedmiller, M.A.: Playing atari with deep reinforcement learning. arXiv:1312.5602 (2013)"},{"key":"346_CR19","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., Rusu, A.A., Veness, J., Bellemare, M.G., Graves, A., Riedmiller, M.A., Fidjeland, A., Ostrovski, G., Petersen, S., Beattie, C., Sadik, A., Antonoglou, I., King, H., Kumaran, D., Wierstra, D., Legg, S., Hassabis, D.: Human-level control through deep reinforcement learning. Nature 518, 529\u2013533 (2015)","journal-title":"Nature"},{"key":"346_CR20","doi-asserted-by":"publisher","first-page":"2797","DOI":"10.1109\/TITS.2020.2975120","volume":"22","author":"C Nguyen Van Phu","year":"2021","unstructured":"Nguyen Van Phu, C., Farhi, N.: Estimation of urban traffic state with probe vehicles. IEEE Trans. Intell. Transp. Syst. 22, 2797\u20132808 (2021)","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"346_CR21","doi-asserted-by":"crossref","unstructured":"P\u0142aczek, B.: A self-organizing system for urban traffic control based on predictive interval microscopic model. arXiv:1406.1128 (2014)","DOI":"10.1016\/j.engappai.2014.05.004"},{"key":"346_CR22","unstructured":"Stevens, M., Yeh, C.: Reinforcement learning for traffic optimization (2016)"},{"key":"346_CR23","unstructured":"Sutton, R., Barto, A.: Reinforcement learning: an introduction (2nd edn.). http:\/\/incompleteideas.net\/book\/RLbook2020.pdf (2018)"},{"key":"346_CR24","doi-asserted-by":"crossref","unstructured":"Touhbi, S., Babram, M.A., Nguyen-Huu, T., Marilleau, N., Hbid, M.L., Cambier, C., Stinckwich, S.: Adaptive traffic signal control : exploring reward definition for reinforcement learning. In: ANT\/SEIT (2017)","DOI":"10.1016\/j.procs.2017.05.327"},{"key":"346_CR25","unstructured":"van der Pol, E., Oliehoek, F.A.: Coordinated deep reinforcement learners for traffic light control (2016)"},{"key":"346_CR26","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. Trans. Res. Part C-emerging Technol. 36, 177\u2013195 (2013)","journal-title":"Trans. Res. Part C-emerging Technol."},{"key":"346_CR27","unstructured":"Vidali, A., Crociani, L., Vizzari, G., Bandini, S.: A deep reinforcement learning approach to adaptive traffic lights management. In: WOA (2019)"},{"key":"346_CR28","unstructured":"Wang, Z., Schaul, T., Hessel, M., Hasselt, H.V., Lanctot, M., de Freitas, N.: Dueling network architectures for deep reinforcement learning. arXiv:1511.06581 (2016)"},{"key":"346_CR29","doi-asserted-by":"publisher","first-page":"2496","DOI":"10.1145\/3219819.3220096","volume-title":"IntelliLight: A Reinforcement Learning Approach for Intelligent Traffic Light Control","author":"H Wei","year":"2018","unstructured":"Wei, H., Zheng, G., Yao, H., Li, Z.: IntelliLight: A Reinforcement Learning Approach for Intelligent Traffic Light Control, pp 2496\u20132505. Association for Computing Machinery, New York (2018). ISBN 9781450355520. https:\/\/doi.org\/10.1145\/3219819.3220096"},{"key":"346_CR30","doi-asserted-by":"crossref","unstructured":"Wei, H., Chen, C., Zheng, G., Wu, K., Gayah, V.V., Xu, K., Li, Z.J.: 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 (2019a)","DOI":"10.1145\/3292500.3330949"},{"key":"346_CR31","doi-asserted-by":"publisher","unstructured":"Wei, H., Xu, N., Zhang, H., Zheng, G., Zang, X., Chen, C., Zhang, W., Zhu, Y., Xu, K., Li, Z.: Colight: Learning network-level cooperation for traffic signal control. In: Proceedings of the 28th ACM international conference on information and knowledge management, CIKM \u201919, pp. 1913\u20131922. New York. Association for Computing Machinery. ISBN 9781450369763. https:\/\/doi.org\/10.1145\/3357384.3357902 (2019b)","DOI":"10.1145\/3357384.3357902"},{"key":"346_CR32","unstructured":"Wei, H., Zheng, G., Gayah, V.V., Li, Z.J.: A survey on traffic signal control methods. arXiv:1904.08117 (2019c)"},{"key":"346_CR33","doi-asserted-by":"publisher","unstructured":"Yan, S., Zhang, J., B\u00fcscher, D., Burgard, W.: Efficiency and equity are both essential: A generalized traffic signal controller with deep reinforcement learning. In: 2020 IEEE\/RSJ international conference on intelligent robots and systems (IROS), pp. 5526\u20135533. https:\/\/doi.org\/10.1109\/IROS45743.2020.9340784 (2020)","DOI":"10.1109\/IROS45743.2020.9340784"},{"key":"346_CR34","doi-asserted-by":"crossref","unstructured":"Zhang, R., Leteurtre, R., Striner, B., Alanazi, A.S., Alghafis, A., Tonguz, O.K.: Partially detected intelligent traffic signal control: environmental adaptation. In: 2019 18th IEEE international conference on machine learning and applications (ICMLA), pp. 1956\u20131960 (2019)","DOI":"10.1109\/ICMLA.2019.00314"},{"key":"346_CR35","doi-asserted-by":"publisher","first-page":"404","DOI":"10.1109\/TITS.2019.2958859","volume":"22","author":"R Zhang","year":"2021","unstructured":"Zhang, R., Ishikawa, A., Wang, W., Striner, B., Tonguz, O.K.: Using reinforcement learning with partial vehicle detection for intelligent traffic signal control. IEEE Trans. Intell. Transp. Syst. 22, 404\u2013415 (2021)","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"346_CR36","doi-asserted-by":"publisher","unstructured":"Zheng, G., Xiong, Y., Zang, X., Feng, J., Wei, H., Zhang, H., Li, Y., Xu, K., Li, Z.: Learning phase competition for traffic signal control. In: Proceedings of the 28th ACM international conference on information and knowledge management, CIKM \u201919, pp. 1963\u20131972. New York. Association for Computing Machinery. ISBN 9781450369763. https:\/\/doi.org\/10.1145\/3357384.3357900 (2019)","DOI":"10.1145\/3357384.3357900"}],"container-title":["International Journal of Intelligent Transportation Systems Research"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13177-023-00346-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s13177-023-00346-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13177-023-00346-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,13]],"date-time":"2024-10-13T13:19:41Z","timestamp":1728825581000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s13177-023-00346-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,2,2]]},"references-count":36,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2023,4]]}},"alternative-id":["346"],"URL":"https:\/\/doi.org\/10.1007\/s13177-023-00346-4","relation":{},"ISSN":["1348-8503","1868-8659"],"issn-type":[{"value":"1348-8503","type":"print"},{"value":"1868-8659","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,2,2]]},"assertion":[{"value":"11 July 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 January 2023","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 January 2023","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 February 2023","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"<!--Emphasis Type='Bold' removed-->Conflict of Interests"}}]}}