{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,21]],"date-time":"2026-07-21T14:24:57Z","timestamp":1784643897093,"version":"3.55.0"},"reference-count":43,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2023,7,1]],"date-time":"2023-07-01T00:00:00Z","timestamp":1688169600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2023,7,1]],"date-time":"2023-07-01T00:00:00Z","timestamp":1688169600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2023,7,1]],"date-time":"2023-07-01T00:00:00Z","timestamp":1688169600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2023,7,1]],"date-time":"2023-07-01T00:00:00Z","timestamp":1688169600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2023,7,1]],"date-time":"2023-07-01T00:00:00Z","timestamp":1688169600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2023,7,1]],"date-time":"2023-07-01T00:00:00Z","timestamp":1688169600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,7,1]],"date-time":"2023-07-01T00:00:00Z","timestamp":1688169600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.15223\/policy-004"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Information Sciences"],"published-print":{"date-parts":[[2023,7]]},"DOI":"10.1016\/j.ins.2023.03.087","type":"journal-article","created":{"date-parts":[[2023,3,17]],"date-time":"2023-03-17T21:33:36Z","timestamp":1679088816000},"page":"55-72","update-policy":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":53,"special_numbering":"C","title":["Hierarchical graph multi-agent reinforcement learning for traffic signal control"],"prefix":"10.1016","volume":"634","author":[{"ORCID":"https:\/\/2.zoppoz.workers.dev:443\/https\/orcid.org\/0000-0003-2436-0580","authenticated-orcid":false,"given":"Shantian","family":"Yang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.ins.2023.03.087_b0005","article-title":"Pollution and congestion in urban areas: The effects of low emission zones","volume":"26\u201327","author":"Bernardo","year":"2021","journal-title":"Econ. Transport."},{"issue":"4","key":"10.1016\/j.ins.2023.03.087_b0010","doi-asserted-by":"crossref","first-page":"494","DOI":"10.1016\/j.cstp.2018.06.002","article-title":"Tackling urban traffic congestion: the experience of London, Stockholm and Singapore","volume":"6","author":"Metz","year":"2018","journal-title":"Case Stud. Transport Policy"},{"key":"10.1016\/j.ins.2023.03.087_b0015","doi-asserted-by":"crossref","unstructured":"P. Varaiya. The max-pressure controller for arbitrary networks of signalized intersections. Complex Networks and Dynamic System, 27-66, 2013. https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.1007\/978-1-4614-6243-9_2.","DOI":"10.1007\/978-1-4614-6243-9_2"},{"key":"10.1016\/j.ins.2023.03.087_b0020","doi-asserted-by":"crossref","first-page":"335","DOI":"10.1016\/j.isatra.2016.10.011","article-title":"An optimal general type-2 fuzzy controller for Urban Traffic Network","volume":"66","author":"Khooban","year":"2017","journal-title":"ISA Trans."},{"issue":"3","key":"10.1016\/j.ins.2023.03.087_b0025","doi-asserted-by":"crossref","first-page":"261","DOI":"10.1109\/TITS.2006.874716","article-title":"Neural networks for real-time traffic signal control","volume":"7","author":"Srinivasan","year":"2006","journal-title":"IEEE Trans. Intelligent Transport. Syst."},{"key":"10.1016\/j.ins.2023.03.087_b0030","doi-asserted-by":"crossref","first-page":"412","DOI":"10.1109\/TITS.2010.2091408","article-title":"Reinforcement learning with function approximation for traffic signal control","volume":"12","author":"Prashanth","year":"2011","journal-title":"IEEE Trans. Intelligent Transport. Syst."},{"issue":"7540","key":"10.1016\/j.ins.2023.03.087_b0035","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"Mnih","year":"2015","journal-title":"Nature"},{"key":"10.1016\/j.ins.2023.03.087_b0040","unstructured":"Z. Wang, T. Schaul, M. Hessel. Dueling network architectures for deep reinforcement learning. In 33rd International Conference on Machine Learning (ICML), 4:2939-2947, 2016."},{"key":"10.1016\/j.ins.2023.03.087_b0045","unstructured":"V. Mnih, A.P. Badia, L. Mirza, et al. Asynchronous methods for deep reinforcement learning. In 33rd International Conference on Machine Learning (ICML), 4:2850-2869,2016."},{"key":"10.1016\/j.ins.2023.03.087_b0050","doi-asserted-by":"crossref","first-page":"249","DOI":"10.1016\/j.inffus.2022.08.001","article-title":"An inductive heterogeneous graph attention-based multi-agent deep graph infomax algorithm for adaptive traffic signal control","volume":"88","author":"Yang","year":"2022","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.ins.2023.03.087_b0055","doi-asserted-by":"crossref","first-page":"100425","DOI":"10.1016\/j.trip.2021.100425","article-title":"Deep reinforcement learning in transportation research: A review","volume":"11","author":"Parvez Farazi","year":"2021","journal-title":"Transport. Res. Interdiscip. Perspectives"},{"key":"10.1016\/j.ins.2023.03.087_b0060","doi-asserted-by":"crossref","first-page":"104855","DOI":"10.1016\/j.knosys.2019.07.026","article-title":"Cooperative traffic signal control using multi-step return and off-policy asynchronous advantage actor-critic graph algorithm","volume":"183","author":"Yang","year":"2019","journal-title":"Knowledge-Based Syst."},{"issue":"8","key":"10.1016\/j.ins.2023.03.087_b0065","doi-asserted-by":"crossref","first-page":"7426","DOI":"10.1109\/TVT.2021.3090796","article-title":"Independent reinforcement learning for weakly cooperative multiagent traffic control problem","volume":"70","author":"Zhang","year":"2021","journal-title":"IEEE Trans. Vehicular Technol."},{"key":"10.1016\/j.ins.2023.03.087_b0070","doi-asserted-by":"crossref","unstructured":"Z. Zeng. GraphLight: Graph-based Reinforcement Learning for Traffic Signal Control. In 6th International Conference on Computer and Communication Systems, pp. 645-650. 2021. https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.1109\/ICCCS52626.2021.9449147.","DOI":"10.1109\/ICCCS52626.2021.9449147"},{"key":"10.1016\/j.ins.2023.03.087_b0075","doi-asserted-by":"crossref","first-page":"106708","DOI":"10.1016\/j.knosys.2020.106708","article-title":"A semi-decentralized feudal multi-agent learned-goal algorithm for multi-intersection traffic signal control","volume":"213","author":"Yang","year":"2021","journal-title":"Knowledge-Based Syst."},{"key":"10.1016\/j.ins.2023.03.087_b0080","first-page":"2","article-title":"Heterogeneous multi-agent deep reinforcement learning for traffic lights control","volume":"2259","author":"Calvo","year":"2018","journal-title":"CEUR Workshop Proc."},{"key":"10.1016\/j.ins.2023.03.087_b0085","doi-asserted-by":"crossref","unstructured":"X. Zang, H. Yao, G. Zheng, et al. Metalight: Value-based meta reinforcement learning for traffic signal control. In 34th AAAI conference on artificial intelligence, 34:1153-1160, 2020.","DOI":"10.1609\/aaai.v34i01.5467"},{"key":"10.1016\/j.ins.2023.03.087_b0090","doi-asserted-by":"crossref","first-page":"265","DOI":"10.1016\/j.neunet.2021.03.015","article-title":"IHG-MA: Inductive heterogeneous graph multi-agent reinforcement learning for multi-intersection traffic signal control","volume":"139","author":"Yang","year":"2021","journal-title":"Neural Networks"},{"key":"10.1016\/j.ins.2023.03.087_b0095","unstructured":"A. Vaswani, N. Shazeer, N. Parmar, et al. Attention is all you need. In 31 Neural Information Processing Systems (NIPS), 2017:5999-6009, 2017."},{"issue":"8","key":"10.1016\/j.ins.2023.03.087_b0100","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long short-term memory","volume":"9","author":"Hochreiter","year":"1997","journal-title":"Neural Comput."},{"issue":"3","key":"10.1016\/j.ins.2023.03.087_b0105","doi-asserted-by":"crossref","first-page":"1086","DOI":"10.1109\/TITS.2019.2901791","article-title":"Multi-agent deep reinforcement learning for large-scale traffic signal control","volume":"21","author":"Chu","year":"2020","journal-title":"IEEE Trans. Intelligent Transport. Syst."},{"key":"10.1016\/j.ins.2023.03.087_b0110","unstructured":"N.K. Thomas and M. Welling. Semi-supervised classification with graph convolutional networks. In 5th International Conference on Learning Representation (ICLR), 2017."},{"key":"10.1016\/j.ins.2023.03.087_b0115","unstructured":"L.H. William, Y. Rex, L. Jure. Inductive representation learning on large graphs. In 31th Advances in Neural Information Processing Systems (NIPS), pp. 1025-1035, 2017."},{"issue":"7","key":"10.1016\/j.ins.2023.03.087_b0120","doi-asserted-by":"crossref","first-page":"7496","DOI":"10.1109\/TITS.2021.3070835","article-title":"Ig-rl: Inductive graph reinforcement learning for massive-scale traffic signal control","volume":"23","author":"Devailly","year":"2021","journal-title":"IEEE Trans. Intelligent Transport. Syst."},{"key":"10.1016\/j.ins.2023.03.087_b0125","unstructured":"Z. Dwiel, M. Candadai, et al. Hierarchical policy learning is sensitive to goal space design. In 36th International Conference on Machine Learning (ICML), 2019."},{"key":"10.1016\/j.ins.2023.03.087_b0130","unstructured":"P. Velickovic, G. Cucurull, A. Casanova et al. Graph attention networks. In 6th International Conference on Learning Representation (ICLR), 2018."},{"key":"10.1016\/j.ins.2023.03.087_b0135","doi-asserted-by":"crossref","unstructured":"S. Michael, N. K. Thomas, B. Peter, et al. Modeling relational data with graph convolutional networks. In European Semantic Web Conference, pp. 593-607, 2018. https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.1007\/978-3-319-93417-4_38.","DOI":"10.1007\/978-3-319-93417-4_38"},{"key":"10.1016\/j.ins.2023.03.087_b0140","doi-asserted-by":"crossref","unstructured":"S. Yang, B. Yang. A Meta Multi-agent Reinforcement Learning Algorithm for Multi-intersection Traffic Signal Control. In 19th International Conference on Dependable, Autonomic and Secure Computing (DASC 2021), pp. 18-25, 2021. https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.1109\/DASC-PICom-CBDCom-CyberSciTech52372.2021.00019.","DOI":"10.1109\/DASC-PICom-CBDCom-CyberSciTech52372.2021.00019"},{"key":"10.1016\/j.ins.2023.03.087_b0145","unstructured":"R.Lowe, Y. Wu, A. Tamar, I. Mordatch. Multi-agent actor-critic for mixed cooperative-competitive environments. In 31th Neural Information Processing Systems (NIPS), 2017:6380-6391, 2017."},{"key":"10.1016\/j.ins.2023.03.087_b0150","unstructured":"R. Hjelm, K. Grewal, P. Bachman, et al. Learning deep representations by mutual information estimation and maximization. In 7th International Conference on Learning Representation (ICLR), 2019."},{"key":"10.1016\/j.ins.2023.03.087_b0155","unstructured":"M. I. Belghazi, A. Baratin, S.Rajeswar, et al. Mine: mutual information neural estimation. In 35rd International Conference on Machine Learning (ICML), 2:864-873, 2018."},{"key":"10.1016\/j.ins.2023.03.087_b0160","doi-asserted-by":"crossref","unstructured":"H. Tong, C. Faloutsos, J. Pan. Fast random walk with restart and its applications. In 6th International Conference on Data Mining, pp.613-622, 2006. https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.1109\/ICDM.2006.70.","DOI":"10.1109\/ICDM.2006.70"},{"key":"10.1016\/j.ins.2023.03.087_b0165","series-title":"Reinforcement learning: An introduction","author":"Sutton","year":"2018"},{"key":"10.1016\/j.ins.2023.03.087_b0170","unstructured":"C. Finn, P. Abbeel S. Levine. Model-agnostic meta learning for fast adaptation of deep networks. In 34th International Conference on Machine Learning (ICML), 3:1856-1868, 2017."},{"key":"10.1016\/j.ins.2023.03.087_b0175","unstructured":"J. Chung, C. Gulcehre, K. Cho and Y. Bengio. Empirical evaluation of gated recurrent neural networks on sequence modeling. In 28th Neural Information Processing Systems (NIPS), NIPS Workshop on Deep Learning, 2014."},{"key":"10.1016\/j.ins.2023.03.087_b0180","unstructured":"J. You, R. Ying, J. Leskovec. Position-aware Graph Neural Networks. In 36th International Conference on Machine Learning (ICML), pp. 12372-12381, 2019."},{"key":"10.1016\/j.ins.2023.03.087_b0185","unstructured":"L. Quo, M. Tomas. Distributed representations of sentences and documents. In 31th International Conference on Machine Learning (ICML), 4:2931-2939, 2014."},{"key":"10.1016\/j.ins.2023.03.087_b0190","unstructured":"P. Veli\u00a3kovi\u00a2, W. Fedus, W.L. Hamilton, et al. Deep graph infomax. In 7th International Conference on Learning Representation (ICLR), 2019."},{"key":"10.1016\/j.ins.2023.03.087_b0195","unstructured":"T. Haarnoja, A. Zhou, P. Abbeel, et al. Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor. In 35th International Conference on Machine Learning (ICML), 5:2976-2989, 2018."},{"key":"10.1016\/j.ins.2023.03.087_b0200","unstructured":"J. Foerster, N. Nardelli, G. Farquhar. Stabilising experience replay for deep multi-agent reinforcement learning. In 34th International Conference on Machine Learning (ICML), 70:1146-1155, 2017."},{"key":"10.1016\/j.ins.2023.03.087_b0205","unstructured":"N. Kheterpal, K. Parvate, C. Wu, et al. Flow: Deep reinforcement learning for control in sumo. 2018. https:\/\/2.zoppoz.workers.dev:443\/https\/flow-project.github.io\/papers\/Flow Deep Reinforcement Learning for Control in SUMO.pdf."},{"key":"10.1016\/j.ins.2023.03.087_b0210","unstructured":"T. Martin, K. Arne. Traffic flow dynamics. Berlin, Heidelberg: Springer Berlin Heidelberg, pp. 1928-1937, 2013."},{"key":"10.1016\/j.ins.2023.03.087_b0215","doi-asserted-by":"crossref","unstructured":"R. Cipolla, Y. Gal, A. Kendall. Multi-task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics. In 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 7482-7491, 2018. https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.1109\/CVPR.2018.00781.","DOI":"10.1109\/CVPR.2018.00781"}],"container-title":["Information Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/api.elsevier.com\/content\/article\/PII:S0020025523003973?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/api.elsevier.com\/content\/article\/PII:S0020025523003973?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2025,9,17]],"date-time":"2025-09-17T06:06:44Z","timestamp":1758089204000},"score":1,"resource":{"primary":{"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/linkinghub.elsevier.com\/retrieve\/pii\/S0020025523003973"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7]]},"references-count":43,"alternative-id":["S0020025523003973"],"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.1016\/j.ins.2023.03.087","relation":{},"ISSN":["0020-0255"],"issn-type":[{"value":"0020-0255","type":"print"}],"subject":[],"published":{"date-parts":[[2023,7]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Hierarchical graph multi-agent reinforcement learning for traffic signal control","name":"articletitle","label":"Article Title"},{"value":"Information Sciences","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.1016\/j.ins.2023.03.087","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2023 Elsevier Inc. All rights reserved.","name":"copyright","label":"Copyright"}]}}