{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T02:59:55Z","timestamp":1781146795869,"version":"3.54.1"},"reference-count":37,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62376048"],"award-info":[{"award-number":["62376048"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100007129","name":"Shandong Province Natural Science Foundation","doi-asserted-by":"publisher","award":["ZR2022LZH002"],"award-info":[{"award-number":["ZR2022LZH002"]}],"id":[{"id":"10.13039\/501100007129","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neural Networks"],"published-print":{"date-parts":[[2026,9]]},"DOI":"10.1016\/j.neunet.2026.108909","type":"journal-article","created":{"date-parts":[[2026,3,28]],"date-time":"2026-03-28T16:11:04Z","timestamp":1774714264000},"page":"108909","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Using a single actor to output personalized policy for different intersections"],"prefix":"10.1016","volume":"201","author":[{"given":"Kailing","family":"Zhou","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9157-6050","authenticated-orcid":false,"given":"Chengwei","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Furui","family":"Zhan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wanting","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yihong","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.neunet.2026.108909_bib0001","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2021.114580","article-title":"Hierarchical traffic signal optimization using reinforcement learning and traffic prediction with long-short term memory","volume":"171","author":"Abdoos","year":"2021","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.neunet.2026.108909_bib0002","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"3414","article-title":"Toward a thousand lights: Decentralized deep reinforcement learning for large-scale traffic signal control","volume":"vol. 34","author":"Chen","year":"2020"},{"key":"10.1016\/j.neunet.2026.108909_bib0003","first-page":"1","article-title":"Learning multi-intersection traffic signal control via coevolutionary multi-agent reinforcement learning","author":"Chen","year":"2024","journal-title":"IEEE Transactions on Intelligent Transportation Systems"},{"key":"10.1016\/j.neunet.2026.108909_bib0004","series-title":"International conference on machine learning","first-page":"1989","article-title":"Scaling multi-agent reinforcement learning with selective parameter sharing","author":"Christianos","year":"2021"},{"issue":"3","key":"10.1016\/j.neunet.2026.108909_bib0005","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":"2019","journal-title":"IEEE Transactions on Intelligent Transportation Systems"},{"issue":"7","key":"10.1016\/j.neunet.2026.108909_bib0006","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 Transactions on Intelligent Transportation Systems"},{"key":"10.1016\/j.neunet.2026.108909_bib0007","series-title":"Proceedings of the 31st ACM international conference on information & knowledge management","first-page":"478","article-title":"Monitorlight: Reinforcement learning-based traffic signal control using mixed pressure monitoring","author":"Fang","year":"2022"},{"issue":"8","key":"10.1016\/j.neunet.2026.108909_bib0008","doi-asserted-by":"crossref","first-page":"12572","DOI":"10.1109\/TITS.2021.3115240","article-title":"Multi-agent transfer reinforcement learning with multi-view encoder for adaptive traffic signal control","volume":"23","author":"Ge","year":"2021","journal-title":"IEEE Transactions on Intelligent Transportation Systems"},{"issue":"7","key":"10.1016\/j.neunet.2026.108909_bib0009","doi-asserted-by":"crossref","first-page":"7619","DOI":"10.1109\/TITS.2024.3352446","article-title":"Large-scale traffic signal control using constrained network partition and adaptive deep reinforcement learning","volume":"25","author":"Gu","year":"2024","journal-title":"IEEE Transactions on Intelligent Transportation Systems"},{"key":"10.1016\/j.neunet.2026.108909_bib0010","first-page":"1024","article-title":"Inductive representation learning on large graphs","volume":"30","author":"Hamilton","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"issue":"1","key":"10.1016\/j.neunet.2026.108909_bib0011","doi-asserted-by":"crossref","first-page":"262","DOI":"10.1109\/TCYB.2021.3087228","article-title":"Network-scale traffic signal control via multiagent reinforcement learning with deep spatiotemporal attentive network","volume":"53","author":"Huang","year":"2021","journal-title":"IEEE Transactions on Cybernetics"},{"key":"10.1016\/j.neunet.2026.108909_bib0012","series-title":"Proceedings of the 37th international conference on machine learning","first-page":"5132","article-title":"SCAFFOLD: Stochastic controlled averaging for federated learning","volume":"vol. 119","author":"Karimireddy","year":"2020"},{"key":"10.1016\/j.neunet.2026.108909_bib0013","unstructured":"Koonce, P., Rodegerdts, L., Lee, K., Quayle, S., Beaird, S., Braud, C., Bonneson, J. A., Tarnoff, P., & Ii, T. (2008). Traffic signal timing manual,."},{"key":"10.1016\/j.neunet.2026.108909_bib0014","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"11595","article-title":"Contrastive identity-aware learning for multi-agent value decomposition","volume":"vol. 37","author":"Liu","year":"2023"},{"key":"10.1016\/j.neunet.2026.108909_bib0015","series-title":"Proceedings of the thirty-second international joint conference on artificial intelligence","first-page":"199","article-title":"Gplight: Grouped multi-agent reinforcement learning for large-scale traffic signal control","author":"Liu","year":"2023"},{"key":"10.1016\/j.neunet.2026.108909_bib0016","series-title":"Proceedings of the 19th international conference on autonomous agents and multiagent systems (AAMAS)","doi-asserted-by":"crossref","first-page":"816","DOI":"10.65109\/UXZA9095","article-title":"Feudal multi-agent deep reinforcement learning for traffic signal control","author":"Ma","year":"2020"},{"key":"10.1016\/j.neunet.2026.108909_bib0017","doi-asserted-by":"crossref","first-page":"396","DOI":"10.1016\/j.neunet.2023.07.027","article-title":"Ccgn: Centralized collaborative graphical transformer multi-agent reinforcement learning for multi-intersection signal free-corridor","volume":"166","author":"Mukhtar","year":"2023","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2026.108909_bib0018","doi-asserted-by":"crossref","first-page":"1092","DOI":"10.1109\/ACCESS.2023.3345343","article-title":"Large-scale traffic signal control based on multi-agent q-learning and pressure","volume":"12","author":"Qi","year":"2024","journal-title":"IEEE Access"},{"key":"10.1016\/j.neunet.2026.108909_bib0019","series-title":"4th international conference on learning representations","article-title":"High-dimensional continuous control using generalized advantage estimation","author":"Schulman","year":"2016"},{"key":"10.1016\/j.neunet.2026.108909_bib0020","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., & Klimov, O. (2017). Proximal policy optimization algorithms. arXiv: 1707.06347."},{"key":"10.1016\/j.neunet.2026.108909_bib0021","first-page":"1","article-title":"Heterogeneous traffic intersections control design based on reinforcement learning","author":"Shen","year":"2023","journal-title":"IET Intelligent Transport Systems"},{"key":"10.1016\/j.neunet.2026.108909_bib0022","series-title":"The max-pressure controller for arbitrary networks of signalized intersections","first-page":"27","author":"Varaiya","year":"2013"},{"issue":"20","key":"10.1016\/j.neunet.2026.108909_bib0023","first-page":"10","article-title":"Graph attention networks","volume":"1050","author":"Velickovic","year":"2017","journal-title":"Stat"},{"issue":"6","key":"10.1016\/j.neunet.2026.108909_bib0024","doi-asserted-by":"crossref","first-page":"2228","DOI":"10.1109\/TMC.2020.3033782","article-title":"Stmarl: A spatio-temporal multi-agent reinforcement learning approach for cooperative traffic light control","volume":"21","author":"Wang","year":"2020","journal-title":"IEEE Transactions on Mobile Computing"},{"key":"10.1016\/j.neunet.2026.108909_bib0025","series-title":"Proceedings of the 25th ACM SIGKDD international conference on knowledge discovery & data mining","first-page":"1290","article-title":"Presslight: Learning max pressure control to coordinate traffic signals in arterial network","author":"Wei","year":"2019"},{"key":"10.1016\/j.neunet.2026.108909_bib0026","series-title":"Proceedings of the 28th ACM international conference on information and knowledge management","first-page":"1913","article-title":"Colight: Learning network-level cooperation for traffic signal control","author":"Wei","year":"2019"},{"key":"10.1016\/j.neunet.2026.108909_bib0027","series-title":"Proceedings of the 24th ACM SIGKDD international conference on knowledge discovery & data mining","first-page":"2496","article-title":"Intellilight: A reinforcement learning approach for intelligent traffic light control","author":"Wei","year":"2018"},{"key":"10.1016\/j.neunet.2026.108909_bib0028","article-title":"Efficient pressure: Improving efficiency for signalized intersections","volume":"abs\/2112.02336","author":"Wu","year":"2021","journal-title":"CoRR"},{"key":"10.1016\/j.neunet.2026.108909_bib0029","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"669","article-title":"Hierarchically and cooperatively learning traffic signal control","volume":"vol. 35","author":"Xu","year":"2021"},{"issue":"6","key":"10.1016\/j.neunet.2026.108909_bib0030","doi-asserted-by":"crossref","first-page":"6248","DOI":"10.1007\/s10489-022-03208-w","article-title":"Graph cooperation deep reinforcement learning for ecological urban traffic signal control","volume":"53","author":"Yan","year":"2023","journal-title":"Applied Intelligence"},{"key":"10.1016\/j.neunet.2026.108909_bib0031","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.neunet.2026.108909_bib0032","doi-asserted-by":"crossref","first-page":"243","DOI":"10.1016\/j.inffus.2023.02.009","article-title":"Causal inference multi-agent reinforcement learning for traffic signal control","volume":"94","author":"Yang","year":"2023","journal-title":"Information Fusion"},{"key":"10.1016\/j.neunet.2026.108909_bib0033","series-title":"Proceedings of the 37th International Conference on Neural Information Processing Systems","article-title":"Automatic grouping for efficient cooperative multi-agent reinforcement learning","volume":"36","author":"Zang","year":"2024"},{"issue":"8","key":"10.1016\/j.neunet.2026.108909_bib0034","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 Transactions on Vehicular Technology"},{"issue":"12","key":"10.1016\/j.neunet.2026.108909_bib0035","doi-asserted-by":"crossref","first-page":"25157","DOI":"10.1109\/TITS.2022.3173490","article-title":"Neighborhood cooperative multiagent reinforcement learning for adaptive traffic signal control in epidemic regions","volume":"23","author":"Zhang","year":"2022","journal-title":"IEEE Transactions on Intelligent Transportation Systems"},{"key":"10.1016\/j.neunet.2026.108909_bib0036","series-title":"Neural networks","first-page":"1","article-title":"A leader-following paradigm based deep reinforcement learning method for multi-agent cooperation games","volume":"vol. 156","author":"Zhang","year":"2022"},{"key":"10.1016\/j.neunet.2026.108909_bib0037","series-title":"Proceedings of the 28th ACM international conference on information and knowledge management","first-page":"1963","article-title":"Learning phase competition for traffic signal control","author":"Zheng","year":"2019"}],"container-title":["Neural Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026003709?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026003709?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T02:52:37Z","timestamp":1781146357000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0893608026003709"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":37,"alternative-id":["S0893608026003709"],"URL":"https:\/\/doi.org\/10.1016\/j.neunet.2026.108909","relation":{},"ISSN":["0893-6080"],"issn-type":[{"value":"0893-6080","type":"print"}],"subject":[],"published":{"date-parts":[[2026,9]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Using a single actor to output personalized policy for different intersections","name":"articletitle","label":"Article Title"},{"value":"Neural Networks","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neunet.2026.108909","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"108909"}}