{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,12,30]],"date-time":"2024-12-30T19:05:04Z","timestamp":1735585504779},"reference-count":38,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2022,4,1]],"date-time":"2022-04-01T00:00:00Z","timestamp":1648771200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2022,4,1]],"date-time":"2022-04-01T00:00:00Z","timestamp":1648771200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2022,4,1]],"date-time":"2022-04-01T00:00:00Z","timestamp":1648771200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2022,4,1]],"date-time":"2022-04-01T00:00:00Z","timestamp":1648771200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2022,4,1]],"date-time":"2022-04-01T00:00:00Z","timestamp":1648771200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2022,4,1]],"date-time":"2022-04-01T00:00:00Z","timestamp":1648771200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,4,1]],"date-time":"2022-04-01T00:00:00Z","timestamp":1648771200000},"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":["11622538","61673150"],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Knowledge-Based Systems"],"published-print":{"date-parts":[[2022,4]]},"DOI":"10.1016\/j.knosys.2022.108304","type":"journal-article","created":{"date-parts":[[2022,2,3]],"date-time":"2022-02-03T04:24:59Z","timestamp":1643862299000},"page":"108304","update-policy":"http:\/\/dx.doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":46,"special_numbering":"C","title":["Distributed agent-based deep reinforcement learning for large scale traffic signal control"],"prefix":"10.1016","volume":"241","author":[{"ORCID":"http:\/\/orcid.org\/0000-0003-0655-0479","authenticated-orcid":false,"given":"Qiang","family":"Wu","sequence":"first","affiliation":[]},{"ORCID":"http:\/\/orcid.org\/0000-0001-7198-4199","authenticated-orcid":false,"given":"Jianqing","family":"Wu","sequence":"additional","affiliation":[]},{"ORCID":"http:\/\/orcid.org\/0000-0002-9403-7140","authenticated-orcid":false,"given":"Jun","family":"Shen","sequence":"additional","affiliation":[]},{"given":"Bo","family":"Du","sequence":"additional","affiliation":[]},{"ORCID":"http:\/\/orcid.org\/0000-0003-4467-4915","authenticated-orcid":false,"given":"Akbar","family":"Telikani","sequence":"additional","affiliation":[]},{"given":"Mahdi","family":"Fahmideh","sequence":"additional","affiliation":[]},{"given":"Chao","family":"Liang","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"key":"10.1016\/j.knosys.2022.108304_b1","doi-asserted-by":"crossref","first-page":"825","DOI":"10.1016\/j.future.2019.02.058","article-title":"Smart fog based workflow for traffic control networks","volume":"97","author":"Wu","year":"2019","journal-title":"Future Gener. Comput. Syst."},{"key":"10.1016\/j.knosys.2022.108304_b2","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 the 24th ACM SIGKDD International Conference On Knowledge Discovery & Data Mining, 2018, pp. 2496\u20132505.","DOI":"10.1145\/3219819.3220096"},{"year":"2018","series-title":"Deep reinforcement learning for traffic light control in vehicular networks","author":"Liang","key":"10.1016\/j.knosys.2022.108304_b3"},{"key":"10.1016\/j.knosys.2022.108304_b4","doi-asserted-by":"crossref","unstructured":"H. Xu, C. Zhang, J. Wang, D. Ouyang, Y. Zheng, J. Shao, Exploring parameter space with structured noise for meta-reinforcement learning, in: Proceedings of the 29th International Joint Conference on Artificial Intelligence, IJCAI, vol. 190, 2020, pp. 3153\u20133159.","DOI":"10.24963\/ijcai.2020\/436"},{"key":"10.1016\/j.knosys.2022.108304_b5","doi-asserted-by":"crossref","first-page":"431","DOI":"10.1016\/j.future.2020.03.065","article-title":"Deep reinforcement learning for traffic signal control under disturbances: A case study on sunway city, Malaysia","volume":"109","author":"Rasheed","year":"2020","journal-title":"Future Gener. Comput. Syst."},{"key":"10.1016\/j.knosys.2022.108304_b6","article-title":"Empowering the diversity and individuality of option: Residual soft option critic framework","author":"Zhu","year":"2021","journal-title":"IEEE Trans. Neural Netw. Learn. Syst. (TNNLS)"},{"issue":"15","key":"10.1016\/j.knosys.2022.108304_b7","doi-asserted-by":"crossref","first-page":"4291","DOI":"10.3390\/s20154291","article-title":"An edge based multi-agent auto communication method for traffic light control","volume":"20","author":"Wu","year":"2020","journal-title":"Sensors"},{"issue":"5","key":"10.1016\/j.knosys.2022.108304_b8","doi-asserted-by":"crossref","first-page":"4461","DOI":"10.1007\/s11227-020-03443-3","article-title":"Intelligent traffic light under fog computing platform in data control of real-time traffic flow","volume":"77","author":"Qin","year":"2021","journal-title":"J. Supercomput."},{"key":"10.1016\/j.knosys.2022.108304_b9","doi-asserted-by":"crossref","first-page":"128","DOI":"10.1016\/j.future.2021.04.018","article-title":"Cooperative multi-agent actor\u2013critic control of traffic network flow based on edge computing","volume":"123","author":"Zhang","year":"2021","journal-title":"Future Gener. Comput. Syst."},{"year":"2018","series-title":"Learning when to communicate at scale in multiagent cooperative and competitive tasks","author":"Singh","key":"10.1016\/j.knosys.2022.108304_b10"},{"key":"10.1016\/j.knosys.2022.108304_b11","doi-asserted-by":"crossref","unstructured":"H. Zhang, Y. Ding, W. Zhang, CityFlow: A multi-agent reinforcement learning environment for large scale city traffic scenario, in: The Web Conference 2019 - Proceedings of the World Wide Web Conference (WWW), 2019, pp. 3620\u20133624.","DOI":"10.1145\/3308558.3314139"},{"key":"10.1016\/j.knosys.2022.108304_b12","doi-asserted-by":"crossref","unstructured":"D. Ouyang, J. Shao, Y. Zhang, Y. Yang, H.T. Shen, Video-based Person re-identification via self-paced learning and deep reinforcement learning framework, in: Proceedings of the 26th ACM International Conference on Multimedia, ACM MM, 2018, pp. 1562\u20131570.","DOI":"10.1145\/3240508.3240622"},{"issue":"3","key":"10.1016\/j.knosys.2022.108304_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.knosys.2022.108304_b14","series-title":"13th International IEEE Conference on Intelligent Transportation Systems","first-page":"665","article-title":"An agent-based learning towards decentralized and coordinated traffic signal control","author":"El-Tantawy","year":"2010"},{"issue":"3","key":"10.1016\/j.knosys.2022.108304_b15","doi-asserted-by":"crossref","first-page":"227","DOI":"10.1080\/15472450.2013.810991","article-title":"Design of reinforcement learning parameters for seamless application of adaptive traffic signal control","volume":"18","author":"El-Tantawy","year":"2014","journal-title":"J. Intell. Transp. Syst."},{"key":"10.1016\/j.knosys.2022.108304_b16","series-title":"17th International IEEE Conference on Intelligent Transportation Systems (ITSC)","first-page":"2529","article-title":"Multi-agent reinforcement learning for traffic signal control","author":"Prabuchandran","year":"2014"},{"year":"2016","series-title":"Using a deep reinforcement learning agent for traffic signal control","author":"Genders","key":"10.1016\/j.knosys.2022.108304_b17"},{"issue":"3","key":"10.1016\/j.knosys.2022.108304_b18","doi-asserted-by":"crossref","first-page":"247","DOI":"10.1109\/JAS.2016.7508798","article-title":"Traffic signal timing via deep reinforcement learning","volume":"3","author":"Li\u00a0Li","year":"2016","journal-title":"IEEE\/CAA J. Automat. Sin."},{"issue":"9","key":"10.1016\/j.knosys.2022.108304_b19","doi-asserted-by":"crossref","first-page":"1005","DOI":"10.1049\/iet-its.2018.5170","article-title":"Value-based deep reinforcement learning for adaptive isolated intersection signal control","volume":"12","author":"Wan","year":"2018","journal-title":"IET Intell. Transp. Syst."},{"issue":"3","key":"10.1016\/j.knosys.2022.108304_b20","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 Trans. Intell. Transp. Syst."},{"key":"10.1016\/j.knosys.2022.108304_b21","series-title":"International Series in Operations Research & Management Science, vol. 145","article-title":"Traffic simulation with sumo\u2013 simulation of urban mobility","author":"Krajzewicz","year":"2015"},{"key":"10.1016\/j.knosys.2022.108304_b22","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2021.107293","article-title":"Edge and fog computing using IoT for direct load optimization and control with flexibility services for citizen energy communities","volume":"228","author":"Oprea","year":"2021","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.knosys.2022.108304_b23","doi-asserted-by":"crossref","first-page":"110","DOI":"10.1016\/j.jnca.2018.07.001","article-title":"Distributed coordination control of traffic network flow using adaptive genetic algorithm based on cloud computing","volume":"119","author":"Zhang","year":"2018","journal-title":"J. Netw. Comput. Appl."},{"key":"10.1016\/j.knosys.2022.108304_b24","doi-asserted-by":"crossref","unstructured":"Q.T. Minh, C.M. Tran, T.A. Le, B.T. Nguyen, T.M. Tran, R.K. Balan, Fogfly: A traffic light optimization solution based on fog computing, in: Proceedings of the 2018 ACM International Joint Conference and 2018 International Symposium on Pervasive and Ubiquitous Computing and Wearable Computers, 2018, pp. 1130\u20131139.","DOI":"10.1145\/3267305.3274169"},{"key":"10.1016\/j.knosys.2022.108304_b25","doi-asserted-by":"crossref","first-page":"84217","DOI":"10.1109\/ACCESS.2019.2925134","article-title":"Phase timing optimization for smart traffic control based on fog computing","volume":"7","author":"Tang","year":"2019","journal-title":"IEEE Access"},{"key":"10.1016\/j.knosys.2022.108304_b26","series-title":"2019 IEEE International Conference On Pervasive Computing And Communications Workshops, PerCom Workshops","first-page":"849","article-title":"Erl: Edge based reinforcement learning for optimized urban traffic light control","author":"Zhou","year":"2019"},{"key":"10.1016\/j.knosys.2022.108304_b27","first-page":"1","article-title":"A fog-based traffic light management strategy (TLMS) based on fuzzy inference engine","author":"Gamel","year":"2021","journal-title":"Neural Comput. Appl."},{"key":"10.1016\/j.knosys.2022.108304_b28","series-title":"2008 47th IEEE Conference on Decision and Control","first-page":"2168","article-title":"Urban traffic control problem a game theory approach","author":"Alvarez","year":"2008"},{"key":"10.1016\/j.knosys.2022.108304_b29","doi-asserted-by":"crossref","unstructured":"M. Khanjary, Using game theory to optimize traffic light of an intersection, in: CINTI 2013 - 14th IEEE International Symposium on Computational Intelligence and Informatics, Proceedings, 2013, pp. 249\u2013253.","DOI":"10.1109\/CINTI.2013.6705201"},{"key":"10.1016\/j.knosys.2022.108304_b30","doi-asserted-by":"crossref","unstructured":"M. Elhenawy, A.A. Elbery, A.A. Hassan, H.A. Rakha, An intersection game-theory-based traffic control algorithm in a connected vehicle environment, in: 2015 IEEE 18th International Conference on Intelligent Transportation Systems, 2015.","DOI":"10.1109\/ITSC.2015.65"},{"issue":"11","key":"10.1016\/j.knosys.2022.108304_b31","doi-asserted-by":"crossref","DOI":"10.1002\/cpe.4077","article-title":"Game theoretic approach on real-time decision making for IoT-based traffic light control","volume":"29","author":"Bui","year":"2017","journal-title":"Concurr. Comput.: Pract. Exp."},{"issue":"Nov","key":"10.1016\/j.knosys.2022.108304_b32","first-page":"1039","article-title":"Nash Q-learning for general-sum stochastic games","volume":"4","author":"Hu","year":"2003","journal-title":"J. Mach. Learn. Res."},{"issue":"6","key":"10.1016\/j.knosys.2022.108304_b33","doi-asserted-by":"crossref","first-page":"1291","DOI":"10.1109\/TSMCC.2012.2218595","article-title":"A survey of actor-critic reinforcement learning: Standard and natural policy gradients","volume":"42","author":"Grondman","year":"2012","journal-title":"IEEE Trans. Syst. Man Cybern. C"},{"key":"10.1016\/j.knosys.2022.108304_b34","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2019.105190","article-title":"Equilibrium optimizer: A novel optimization algorithm","volume":"191","author":"Faramarzi","year":"2020","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.knosys.2022.108304_b35","doi-asserted-by":"crossref","first-page":"271","DOI":"10.1016\/j.knosys.2009.01.003","article-title":"Collaborative learning using service-oriented architecture: A framework design","volume":"22","author":"Chua","year":"2009","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.knosys.2022.108304_b36","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2019.105173","article-title":"Reinforcement learning approach for optimal control of multiple electric locomotives in a heavy-haul freight train: A double-switch-Q-network architecture","volume":"190","author":"Tang","year":"2020","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.knosys.2022.108304_b37","series-title":"International Conference On Machine Learning","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"Mnih","year":"2016"},{"year":"2013","series-title":"Playing atari with deep reinforcement learning","author":"Mnih","key":"10.1016\/j.knosys.2022.108304_b38"}],"container-title":["Knowledge-Based Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S095070512200106X?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S095070512200106X?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2024,4,27]],"date-time":"2024-04-27T17:08:02Z","timestamp":1714237682000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S095070512200106X"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,4]]},"references-count":38,"alternative-id":["S095070512200106X"],"URL":"https:\/\/doi.org\/10.1016\/j.knosys.2022.108304","relation":{},"ISSN":["0950-7051"],"issn-type":[{"type":"print","value":"0950-7051"}],"subject":[],"published":{"date-parts":[[2022,4]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Distributed agent-based deep reinforcement learning for large scale traffic signal control","name":"articletitle","label":"Article Title"},{"value":"Knowledge-Based Systems","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.knosys.2022.108304","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2022 Elsevier B.V. All rights reserved.","name":"copyright","label":"Copyright"}],"article-number":"108304"}}