{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T18:53:47Z","timestamp":1777488827900,"version":"3.51.4"},"reference-count":39,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2022,2,1]],"date-time":"2022-02-01T00:00:00Z","timestamp":1643673600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2022,2,1]],"date-time":"2022-02-01T00:00:00Z","timestamp":1643673600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2022,2,1]],"date-time":"2022-02-01T00:00:00Z","timestamp":1643673600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2022,2,1]],"date-time":"2022-02-01T00:00:00Z","timestamp":1643673600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2022,2,1]],"date-time":"2022-02-01T00:00:00Z","timestamp":1643673600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2022,2,1]],"date-time":"2022-02-01T00:00:00Z","timestamp":1643673600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,2,1]],"date-time":"2022-02-01T00:00:00Z","timestamp":1643673600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100004106","name":"East China Normal University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004106","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2018YFB2101300"],"award-info":[{"award-number":["2018YFB2101300"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61872147"],"award-info":[{"award-number":["61872147"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002855","name":"Ministry of Science and Technology of the People's Republic of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002855","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Journal of Systems Architecture"],"published-print":{"date-parts":[[2022,2]]},"DOI":"10.1016\/j.sysarc.2021.102374","type":"journal-article","created":{"date-parts":[[2021,12,30]],"date-time":"2021-12-30T21:57:27Z","timestamp":1640901447000},"page":"102374","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":41,"special_numbering":"C","title":["IPDALight: Intensity- and phase duration-aware traffic signal control based on Reinforcement Learning"],"prefix":"10.1016","volume":"123","author":[{"given":"Wupan","family":"Zhao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yutong","family":"Ye","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiepin","family":"Ding","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ting","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tongquan","family":"Wei","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3922-0989","authenticated-orcid":false,"given":"Mingsong","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"key":"10.1016\/j.sysarc.2021.102374_b1","doi-asserted-by":"crossref","first-page":"3542","DOI":"10.1016\/j.trpro.2017.05.282","article-title":"Impact of congestion on greenhouse gas emissions for road transport in Mumbai metropolitan region","volume":"25","author":"Bharadwaj","year":"2017","journal-title":"Transp. Res. Procedia"},{"key":"10.1016\/j.sysarc.2021.102374_b2","series-title":"Congestion Costs Each American Nearly 100 H, $1, 400 A Year","year":"2019"},{"key":"10.1016\/j.sysarc.2021.102374_b3","series-title":"Transportation Research Board Meeting","article-title":"Surtrac: Scalable urban traffic control","author":"Smith","year":"2013"},{"issue":"3","key":"10.1016\/j.sysarc.2021.102374_b4","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3068287","article-title":"A survey on reinforcement learning models and algorithms for traffic signal control","volume":"50","author":"Yau","year":"2017","journal-title":"ACM Comput. Surv."},{"key":"10.1016\/j.sysarc.2021.102374_b5","series-title":"A survey on traffic signal control methods","author":"Wei","year":"2019"},{"key":"10.1016\/j.sysarc.2021.102374_b6","first-page":"1","article-title":"Deep reinforcement learning for intelligent transportation systems: A survey","author":"Haydari","year":"2020","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"10.1016\/j.sysarc.2021.102374_b7","doi-asserted-by":"crossref","unstructured":"G. Zheng, Y. Xiong, X. Zang, J. Feng, H. Wei, H. Zhang, Y. Li, K. Xu, Z. Li, Learning phase competition for traffic signal control, in: Proceedings of International Conference on Information and Knowledge Management (CIKM), 2019, pp. 1963\u20131972.","DOI":"10.1145\/3357384.3357900"},{"key":"10.1016\/j.sysarc.2021.102374_b8","doi-asserted-by":"crossref","unstructured":"H. Wei, C. Chen, G. Zheng, K. Wu, V. Gayah, K. Xu, Z. Li, Presslight: Learning max pressure control to coordinate traffic signals in arterial network, in: Proceedings of International Conference on Knowledge Discovery & Data Mining (KDD), 2019, pp. 1290\u20131298.","DOI":"10.1145\/3292500.3330949"},{"key":"10.1016\/j.sysarc.2021.102374_b9","doi-asserted-by":"crossref","unstructured":"H. Wei, N. Xu, H. Zhang, G. Zheng, X. Zang, C. Chen, W. Zhang, Y. Zhu, K. Xu, Z. Li, Colight: Learning network-level cooperation for traffic signal control, in: Proceedings of International Conference on Information and Knowledge Management (CIKM), 2019, pp. 1913\u20131922.","DOI":"10.1145\/3357384.3357902"},{"key":"10.1016\/j.sysarc.2021.102374_b10","doi-asserted-by":"crossref","first-page":"177","DOI":"10.1016\/j.trc.2013.08.014","article-title":"Max pressure control of a network of signalized intersections","volume":"36","author":"Varaiya","year":"2013","journal-title":"Transp. Res. C"},{"key":"10.1016\/j.sysarc.2021.102374_b11","series-title":"On Distributed Communications: I. Introduction to Distributed Communications Networks, Vol. 5","first-page":"193","author":"Baran","year":"1964"},{"key":"10.1016\/j.sysarc.2021.102374_b12","series-title":"Traffic Signal Timing Manual","author":"Koonce","year":"2008"},{"issue":"3","key":"10.1016\/j.sysarc.2021.102374_b13","doi-asserted-by":"crossref","first-page":"278","DOI":"10.1061\/(ASCE)0733-947X(2003)129:3(278)","article-title":"Reinforcement learning for true adaptive traffic signal control","volume":"129","author":"Abdulhai","year":"2003","journal-title":"J. Transp. Eng."},{"key":"10.1016\/j.sysarc.2021.102374_b14","unstructured":"M.A. Wiering, Multi-agent reinforcement learning for traffic light control, in: Proceedings of International Conference on Machine Learning (ICML), 2000, pp. 1151\u20131158."},{"issue":"1","key":"10.1016\/j.sysarc.2021.102374_b15","doi-asserted-by":"crossref","first-page":"40","DOI":"10.1080\/15472450.2017.1387546","article-title":"Learning-based traffic signal control algorithms with neighborhood information sharing: An application for sustainable mobility","volume":"22","author":"Aziz","year":"2018","journal-title":"J. Intell. Transp. Syst."},{"key":"10.1016\/j.sysarc.2021.102374_b16","unstructured":"Watkins, C.J.C. Hellaby, Learning From Delayed Rewards. King\u2019s College, Cambridge United Kingdom, 1989."},{"key":"10.1016\/j.sysarc.2021.102374_b17","series-title":"On-Line Q-Learning using Connectionist Systems","author":"Rummery","year":"1994"},{"key":"10.1016\/j.sysarc.2021.102374_b18","doi-asserted-by":"crossref","first-page":"732","DOI":"10.1016\/j.trc.2017.09.020","article-title":"Adaptive traffic signal control with actor-critic methods in a real-world traffic network with different traffic disruption events","volume":"85","author":"Aslani","year":"2017","journal-title":"Transp. Res. C"},{"issue":"10","key":"10.1016\/j.sysarc.2021.102374_b19","doi-asserted-by":"crossref","first-page":"3900","DOI":"10.1109\/TITS.2019.2906260","article-title":"A multi-objective agent-based control approach with application in intelligent traffic signal system","volume":"20","author":"Jin","year":"2019","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"10.1016\/j.sysarc.2021.102374_b20","series-title":"Using a deep reinforcement learning agent for traffic signal control","author":"Genders","year":"2016"},{"key":"10.1016\/j.sysarc.2021.102374_b21","series-title":"International Conference on Intelligent Transportation Systems (ITSC)","first-page":"2575","article-title":"Microscopic traffic simulation using sumo","author":"Lopez","year":"2018"},{"key":"10.1016\/j.sysarc.2021.102374_b22","series-title":"Adaptive traffic signal control: Deep reinforcement learning algorithm with experience replay and target network","author":"Gao","year":"2017"},{"key":"10.1016\/j.sysarc.2021.102374_b23","doi-asserted-by":"crossref","unstructured":"H. Wei, G. Zheng, H. Yao, Z. Li, Intellilight: A reinforcement learning approach for intelligent traffic light control, in: Proceedings of International Conference on Knowledge Discovery & Data Mining (KDD), 2018, pp. 2496\u20132505.","DOI":"10.1145\/3219819.3220096"},{"key":"10.1016\/j.sysarc.2021.102374_b24","series-title":"Playing atari with deep reinforcement learning","author":"Mnih","year":"2013"},{"issue":"2","key":"10.1016\/j.sysarc.2021.102374_b25","doi-asserted-by":"crossref","first-page":"1243","DOI":"10.1109\/TVT.2018.2890726","article-title":"A deep reinforcement learning network for traffic light cycle control","volume":"68","author":"Liang","year":"2019","journal-title":"IEEE Trans. Veh. Technol."},{"key":"10.1016\/j.sysarc.2021.102374_b26","unstructured":"Z. Wang, T. Schaul, M. Hessel, H. Hasselt, M. Lanctot, N. Freitas, Dueling network architectures for deep reinforcement learning, in: Proceedings of International Conference on Machine Learning (ICML), 2016, pp. 1995\u20132003."},{"key":"10.1016\/j.sysarc.2021.102374_b27","doi-asserted-by":"crossref","unstructured":"W. Chang, D. Roy, S. Zhao, A. Annaswamy, S. Chakraborty, CPS-oriented modeling and control of traffic signals using adaptive back pressure, in: Proceedings of Design, Automation & Test in Europe Conference & Exhibition (DATE), 2020, pp. 1686\u20131691.","DOI":"10.23919\/DATE48585.2020.9116403"},{"key":"10.1016\/j.sysarc.2021.102374_b28","unstructured":"J.A. Calvo, I. Dusparic, Heterogeneous multi-agent deep reinforcement learning for traffic lights control, in: Proceedings of Irish Conference on Artificial Intelligence and Cognitive Science (AICS), 2008, pp. 2\u201313."},{"key":"10.1016\/j.sysarc.2021.102374_b29","unstructured":"J. Foerster, N. Nardelli, G. Farquhar, T. Afouras, P.H. Torr, P. Kohli, S. Whiteson, Stabilising experience replay for deep multi-agent reinforcement learning, in: Proceedings of International Conference on Machine Learning (ICML), 2017, pp. 1146\u20131155."},{"issue":"6","key":"10.1016\/j.sysarc.2021.102374_b30","doi-asserted-by":"crossref","first-page":"2687","DOI":"10.1109\/TCYB.2019.2904742","article-title":"Cooperative deep reinforcement learning for large-scale traffic grid signal control","volume":"50","author":"Tan","year":"2019","journal-title":"IEEE Trans. Cybern."},{"key":"10.1016\/j.sysarc.2021.102374_b31","series-title":"Deep reinforcement learning in large discrete action spaces","author":"Dulac-Arnold","year":"2015"},{"key":"10.1016\/j.sysarc.2021.102374_b32","series-title":"Advances in Dynamic Network Modeling in Complex Transportation Systems","first-page":"27","article-title":"The max-pressure controller for arbitrary networks of signalized intersections","author":"Varaiya","year":"2013"},{"key":"10.1016\/j.sysarc.2021.102374_b33","doi-asserted-by":"crossref","unstructured":"C. Chen, H. Wei, N. Xu, G. Zheng, M. Yang, Y. Xiong, K. Xu, Z. Li, Toward a thousand lights: Decentralized deep reinforcement learning for large-scale traffic signal control, in: Proceedings of AAAI Conference on Artificial Intelligence (AAAI), 2020, pp. 3414\u20133421.","DOI":"10.1609\/aaai.v34i04.5744"},{"key":"10.1016\/j.sysarc.2021.102374_b34","doi-asserted-by":"crossref","unstructured":"H. Zhang, S. Feng, C. Liu, Y. Ding, Y. Zhu, Z. Zhou, W. Zhang, Y. Yu, H. Jin, Z. Li, Cityflow: A multi-agent reinforcement learning environment for large scale city traffic scenario, in: Proceedings of the World Wide Web Conference (WWW), 2019, pp. 3620\u20133624.","DOI":"10.1145\/3308558.3314139"},{"key":"10.1016\/j.sysarc.2021.102374_b35","unstructured":"DQN implementation. https:\/\/github.com\/keon\/deep-q-learning."},{"key":"10.1016\/j.sysarc.2021.102374_b36","unstructured":"Benchmark dataset. https:\/\/traffic-signal-control.github.io\/dataset.html."},{"key":"10.1016\/j.sysarc.2021.102374_b37","series-title":"Traffic Engineering","author":"Roess","year":"1990"},{"key":"10.1016\/j.sysarc.2021.102374_b38","series-title":"Advances in Applied Self-Organizing Systems","first-page":"41","article-title":"Self-organizing traffic lights: A realistic simulation","author":"Cools","year":"2013"},{"key":"10.1016\/j.sysarc.2021.102374_b39","unstructured":"E. Van\u00a0der Pol, F.A. Oliehoek, Coordinated deep reinforcement learners for traffic light control, in: Proceedings of Workshop on Learning, Inference and Control of Multi-Agent Systems, 2016, pp. 1\u20138."}],"container-title":["Journal of Systems Architecture"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1383762121002587?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1383762121002587?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2025,10,24]],"date-time":"2025-10-24T13:34:39Z","timestamp":1761312879000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1383762121002587"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,2]]},"references-count":39,"alternative-id":["S1383762121002587"],"URL":"https:\/\/doi.org\/10.1016\/j.sysarc.2021.102374","relation":{},"ISSN":["1383-7621"],"issn-type":[{"value":"1383-7621","type":"print"}],"subject":[],"published":{"date-parts":[[2022,2]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"IPDALight: Intensity- and phase duration-aware traffic signal control based on Reinforcement Learning","name":"articletitle","label":"Article Title"},{"value":"Journal of Systems Architecture","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.sysarc.2021.102374","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2021 Elsevier B.V. All rights reserved.","name":"copyright","label":"Copyright"}],"article-number":"102374"}}