{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,21]],"date-time":"2026-02-21T20:36:59Z","timestamp":1771706219990,"version":"3.50.1"},"reference-count":52,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2023,12,5]],"date-time":"2023-12-05T00:00:00Z","timestamp":1701734400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,12,5]],"date-time":"2023-12-05T00:00:00Z","timestamp":1701734400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61876138"],"award-info":[{"award-number":["61876138"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Appl Intell"],"published-print":{"date-parts":[[2024,1]]},"DOI":"10.1007\/s10489-023-05197-w","type":"journal-article","created":{"date-parts":[[2023,12,5]],"date-time":"2023-12-05T07:02:31Z","timestamp":1701759751000},"page":"95-112","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["RELight: a random ensemble reinforcement learning based method for traffic light control"],"prefix":"10.1007","volume":"54","author":[{"given":"Jianbin","family":"Huang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4212-5499","authenticated-orcid":false,"given":"Qinglin","family":"Tan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruijie","family":"Qi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"He","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,12,5]]},"reference":[{"key":"5197_CR1","doi-asserted-by":"publisher","first-page":"201","DOI":"10.1007\/s10489-013-0455-3","volume":"40","author":"M Abdoos","year":"2014","unstructured":"Abdoos M, Mozayani N, Bazzan AL (2014) Hierarchical control of traffic signals using q-learning with tile coding. Appl Intell 40:201\u2013213","journal-title":"Appl Intell"},{"key":"5197_CR2","doi-asserted-by":"crossref","unstructured":"Chacha Chen HW, Xu N, Zheng G et al (2020) Toward a thousand lights: decentralized deep reinforcement learning for large-scale traffic signal control. In: Proceedings of the thirty-fourth AAAI conference on artificial intelligence (AAAI\u201920), New York, NY, USA, pp 7\u201312","DOI":"10.1609\/aaai.v34i04.5744"},{"key":"5197_CR3","doi-asserted-by":"crossref","unstructured":"Chen C, Wei H, Xu N et al (2020) Toward a thousand lights: decentralized deep reinforcement learning for large-scale traffic signal control. In: Proceedings of the AAAI conference on artificial intelligence, pp 3414\u20133421","DOI":"10.1609\/aaai.v34i04.5744"},{"key":"5197_CR4","unstructured":"Chen X, Wang C, Zhou Z et al (2021) Randomized ensembled double q-learning: learning fast without a model. In: 9th International conference on learning representations, ICLR 2021, Virtual event, Austria. OpenReview.net, https:\/\/openreview.net\/forum?id=AY8zfZm0tDd. Accessed 3-7 May 2021"},{"key":"5197_CR5","doi-asserted-by":"crossref","unstructured":"Du W, Ye J, Gu J et al (2023) Safelight: a reinforcement learning method toward collision-free traffic signal control. In: Proceedings of the AAAI conference on artificial intelligence, pp 14,801\u201314,810","DOI":"10.1609\/aaai.v37i12.26729"},{"key":"5197_CR6","doi-asserted-by":"publisher","unstructured":"El-Tantawy S, Abdulhai B (2010) An agent-based learning towards decentralized and coordinated traffic signal control. In: 13th International IEEE conference on intelligent transportation systems. IEEE, pp 665\u2013670. https:\/\/doi.org\/10.1109\/ITSC.2010.5625066","DOI":"10.1109\/ITSC.2010.5625066"},{"issue":"3","key":"5197_CR7","doi-asserted-by":"publisher","first-page":"1140","DOI":"10.1109\/TITS.2013.2255286","volume":"14","author":"S El-Tantawy","year":"2013","unstructured":"El-Tantawy S, Abdulhai B, Abdelgawad H (2013) Multiagent reinforcement learning for integrated network of adaptive traffic signal controllers (marlin-atsc): methodology and large-scale application on downtown toronto. IEEE Trans Intell Transp Syst 14(3):1140\u20131150","journal-title":"IEEE Trans Intell Transp Syst"},{"key":"5197_CR8","unstructured":"Fujimoto S, Hoof H, Meger D (2018) Addressing function approximation error in actor-critic methods. In: International conference on machine learning. PMLR, pp 1587\u20131596"},{"key":"5197_CR9","doi-asserted-by":"crossref","unstructured":"Gershenson C (2005) Self-organizing traffic lights. Complex Syst 16(1). http:\/\/www.complex-systems.com\/abstracts\/v16_i01_a02.html","DOI":"10.25088\/ComplexSystems.16.1.29"},{"issue":"11","key":"5197_CR10","doi-asserted-by":"publisher","first-page":"2612","DOI":"10.1109\/TAC.2010.2060245","volume":"55","author":"J Haddad","year":"2010","unstructured":"Haddad J, De Schutter B, Mahalel D et al (2010) Optimal steady-state control for isolated traffic intersections. IEEE Trans Autom Control 55(11):2612\u20132617. https:\/\/doi.org\/10.1109\/TAC.2010.2060245","journal-title":"IEEE Trans Autom Control"},{"key":"5197_CR11","doi-asserted-by":"crossref","unstructured":"van Hasselt H, Guez A, Silver D (2016) Deep reinforcement learning with double q-learning. In: Proceedings of the thirtieth AAAI conference on artificial intelligence, Phoenix, Arizona, USA, vol 30. AAAI Press, pp 2094\u20132100. http:\/\/www.aaai.org\/ocs\/index.php\/AAAI\/AAAI16\/paper\/view\/12389. Accessed 12-17 Feb 2016","DOI":"10.1609\/aaai.v30i1.10295"},{"issue":"4","key":"5197_CR12","doi-asserted-by":"publisher","first-page":"4610","DOI":"10.1007\/s10489-021-02586-x","volume":"52","author":"J Huang","year":"2022","unstructured":"Huang J, Tan Q, Li H et al (2022) Monte carlo tree search for dynamic bike repositioning in bike-sharing systems. Appl Intell 52(4):4610\u20134625. https:\/\/doi.org\/10.1007\/s10489-021-02586-x","journal-title":"Appl Intell"},{"key":"5197_CR13","unstructured":"Hunt P, Robertson D, Bretherton R et al (1981) Scoot-a traffic responsive method of coordinating signals. Tech rep"},{"issue":"1","key":"5197_CR14","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3314402","volume":"3","author":"S Ji","year":"2019","unstructured":"Ji S, Zheng Y, Wang Z et al (2019) A deep reinforcement learning-enabled dynamic redeployment system for mobile ambulances. Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies 3(1):1\u201320. https:\/\/doi.org\/10.1145\/3314402","journal-title":"Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies"},{"key":"5197_CR15","doi-asserted-by":"crossref","unstructured":"Jiang Q, Qin M, Shi S et al (2022) Multi-agent reinforcement learning for traffic signal control through universal communication method. arXiv preprint arXiv:2204.12190","DOI":"10.24963\/ijcai.2022\/535"},{"key":"5197_CR16","unstructured":"Koonce P, Rodegerdts L (2008) Traffic signal timing manual. Tech rep, United States. Federal Highway Administration"},{"issue":"6","key":"5197_CR17","first-page":"1580","volume":"8","author":"H Li","year":"2021","unstructured":"Li H, Huang J, Yuan H et al (2021) A two-phase method to balance the result of distributed graph repartitioning. IEEE Transactions on Big Data 8(6):1580\u20131591","journal-title":"IEEE Transactions on Big Data"},{"issue":"2","key":"5197_CR18","first-page":"1","volume":"13","author":"H Li","year":"2022","unstructured":"Li H, Li X, Su L et al (2022) Deep spatio-temporal adaptive 3d convolutional neural networks for traffic flow prediction. ACM Transactions on Intelligent Systems and Technology (TIST) 13(2):1\u201321","journal-title":"ACM Transactions on Intelligent Systems and Technology (TIST)"},{"key":"5197_CR19","doi-asserted-by":"crossref","unstructured":"Li H, Jin D, Li X et al (2023) Dmgf-net: an efficient dynamic multi-graph fusion network for traffic prediction. ACM Transactions on Knowledge Discovery from Data","DOI":"10.1145\/3586164"},{"issue":"3","key":"5197_CR20","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 FY (2016) Traffic signal timing via deep reinforcement learning. IEEE\/CAA Journal of Automatica Sinica 3(3):247\u2013254","journal-title":"IEEE\/CAA Journal of Automatica Sinica"},{"issue":"2","key":"5197_CR21","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 et al (2019) A deep reinforcement learning network for traffic light cycle control. IEEE Trans Veh Technol 68(2):1243\u20131253","journal-title":"IEEE Trans Veh Technol"},{"key":"5197_CR22","unstructured":"Lillicrap TP, Hunt JJ, Pritzel A et al (2016) Continuous control with deep reinforcement learning. In: 4th International conference on learning representations, ICLR 2016, San Juan, Puerto Rico, Conference track proceedings. arXiv:1509.02971. Accessed 2-4 May 2016"},{"key":"5197_CR23","unstructured":"Lowrie P (1990) Scats, sydney co-ordinated adaptive traffic system: a traffic responsive method of controlling urban traffic"},{"issue":"1","key":"5197_CR24","doi-asserted-by":"publisher","first-page":"160","DOI":"10.1109\/MITS.2022.3144797","volume":"15","author":"F Mao","year":"2022","unstructured":"Mao F, Li Z, Li L (2022) A comparison of deep reinforcement learning models for isolated traffic signal control. IEEE Intell Transp Syst Mag 15(1):160\u2013180","journal-title":"IEEE Intell Transp Syst Mag"},{"issue":"4","key":"5197_CR25","doi-asserted-by":"publisher","first-page":"373","DOI":"10.1057\/jors.1963.61","volume":"14","author":"AJ Miller","year":"1963","unstructured":"Miller AJ (1963) Settings for fixed-cycle traffic signals. Journal of the Operational Research Society 14(4):373\u2013386. https:\/\/doi.org\/10.1057\/jors.1963.61","journal-title":"Journal of the Operational Research Society"},{"key":"5197_CR26","doi-asserted-by":"publisher","unstructured":"Mirchandani P, Head L (2001) A real-time traffic signal control system: architecture, algorithms, and analysis. Transportation Research Part C: Emerging Technologies 9(6):415\u2013432. https:\/\/doi.org\/10.1016\/S0968-090X(00)00047-4, https:\/\/www.sciencedirect.com\/science\/article\/pii\/S0968090X00000474","DOI":"10.1016\/S0968-090X(00)00047-4"},{"issue":"7","key":"5197_CR27","doi-asserted-by":"publisher","first-page":"417","DOI":"10.1049\/iet-its.2017.0153","volume":"11","author":"SS Mousavi","year":"2017","unstructured":"Mousavi SS, Schukat M, Howley E (2017) Traffic light control using deep policy-gradient and value-function-based reinforcement learning. IET Intel Transport Syst 11(7):417\u2013423","journal-title":"IET Intel Transport Syst"},{"key":"5197_CR28","unstructured":"Nikishin E, Schwarzer M, D\u2019Oro P et al (2022) The primacy bias in deep reinforcement learning. In: International conference on machine learning. PMLR, pp 16,828\u201316,847"},{"key":"5197_CR29","doi-asserted-by":"crossref","unstructured":"Nishi T, Otaki K, Hayakawa K et al (2018) Traffic signal control based on reinforcement learning with graph convolutional neural nets. In: 2018 21st International conference on intelligent transportation systems (ITSC). IEEE, pp 877\u2013883","DOI":"10.1109\/ITSC.2018.8569301"},{"key":"5197_CR30","doi-asserted-by":"publisher","first-page":"116,830","DOI":"10.1016\/j.eswa.2022.116830","volume":"199","author":"M Noaeen","year":"2022","unstructured":"Noaeen M, Naik A, Goodman L et al (2022) Reinforcement learning in urban network traffic signal control: a systematic literature review. Expert Syst Appl 199:116,830","journal-title":"Expert Syst Appl"},{"key":"5197_CR31","first-page":"21","volume":"8","author":"E Van der Pol","year":"2016","unstructured":"Van der Pol E, Oliehoek FA (2016) Coordinated deep reinforcement learners for traffic light control. Proceedings of learning, inference and control of multi-agent systems (at NIPS 2016) 8:21\u201338","journal-title":"Proceedings of learning, inference and control of multi-agent systems (at NIPS 2016)"},{"key":"5197_CR32","unstructured":"Roess RP, Prassas ES, McShane WR (2004) Traffic engineering. Pearson\/Prentice Hall"},{"issue":"7587","key":"5197_CR33","doi-asserted-by":"publisher","first-page":"484","DOI":"10.1038\/nature16961","volume":"529","author":"D Silver","year":"2016","unstructured":"Silver D, Huang A, Maddison CJ et al (2016) Mastering the game of go with deep neural networks and tree search. Nature 529(7587):484\u2013489","journal-title":"Nature"},{"issue":"7676","key":"5197_CR34","doi-asserted-by":"publisher","first-page":"354","DOI":"10.1038\/nature24270","volume":"550","author":"D Silver","year":"2017","unstructured":"Silver D, Schrittwieser J, Simonyan K et al (2017) Mastering the game of go without human knowledge. Nature 550(7676):354\u2013359","journal-title":"Nature"},{"key":"5197_CR35","doi-asserted-by":"publisher","DOI":"10.17226\/22097","volume-title":"Signal timing manual","author":"T Urbanik","year":"2015","unstructured":"Urbanik T, Tanaka A, Lozner B et al (2015) Signal timing manual, vol 1. Transportation Research Board Washington, DC"},{"key":"5197_CR36","doi-asserted-by":"publisher","unstructured":"Varaiya P (2013) The max-pressure controller for arbitrary networks of signalized intersections. Springer, New York, NY, pp 27\u201366. https:\/\/doi.org\/10.1007\/978-1-4614-6243-9_2","DOI":"10.1007\/978-1-4614-6243-9_2"},{"key":"5197_CR37","doi-asserted-by":"crossref","unstructured":"Wang M, Wu L, Li J et al (2022) Urban traffic signal control with reinforcement learning from demonstration data. In: 2022 International joint conference on neural networks (IJCNN). IEEE, pp 1\u20138","DOI":"10.1109\/IJCNN55064.2022.9892538"},{"key":"5197_CR38","doi-asserted-by":"publisher","first-page":"103,046","DOI":"10.1016\/j.trc.2021.103046","volume":"125","author":"T Wang","year":"2021","unstructured":"Wang T, Cao J, Hussain A (2021) Adaptive traffic signal control for large-scale scenario with cooperative group-based multi-agent reinforcement learning. Transportation research part C: emerging technologies 125:103,046","journal-title":"Transportation research part C: emerging technologies"},{"key":"5197_CR39","doi-asserted-by":"publisher","unstructured":"Wei H, Zheng G, Yao H et al (2018) Intellilight: a reinforcement learning approach for intelligent traffic light control. In: Proceedings of the 24th ACM SIGKDD International conference on knowledge discovery & data mining, KDD 2018, London, UK. ACM, pp 2496\u20132505. https:\/\/doi.org\/10.1145\/3219819.3220096. Accessed 19-23 Aug 2018","DOI":"10.1145\/3219819.3220096"},{"key":"5197_CR40","doi-asserted-by":"crossref","unstructured":"Wei H, Chen C, Zheng G et al (2019a) 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, pp 1290\u20131298","DOI":"10.1145\/3292500.3330949"},{"key":"5197_CR41","doi-asserted-by":"publisher","unstructured":"Wei H, Xu N, Zhang H et al (2019b) Colight: learning network-level cooperation for traffic signal control. In: Proceedings of the 28th ACM international conference on information and knowledge management, CIKM 2019, Beijing, China. ACM, pp 1913\u20131922. https:\/\/doi.org\/10.1145\/3357384.3357902. Accessed 3-7 Nov 2019","DOI":"10.1145\/3357384.3357902"},{"issue":"2","key":"5197_CR42","doi-asserted-by":"publisher","first-page":"12","DOI":"10.1145\/3447556.3447565","volume":"22","author":"H Wei","year":"2021","unstructured":"Wei H, Zheng G, Gayah V et al (2021) Recent advances in reinforcement learning for traffic signal control: a survey of models and evaluation. ACM SIGKDD Explorations Newsl 22(2):12\u201318","journal-title":"ACM SIGKDD Explorations Newsl"},{"key":"5197_CR43","doi-asserted-by":"publisher","unstructured":"Wei Y, Mao M, Zhao X et al (2020) City metro network expansion with reinforcement learning. In: KDD \u201920: The 26th ACM SIGKDD conference on knowledge discovery and data mining, Virtual event, CA, USA. ACM, pp 2646\u20132656. https:\/\/doi.org\/10.1145\/3394486.3403315. Accessed 23-27 Aug 2020","DOI":"10.1145\/3394486.3403315"},{"key":"5197_CR44","unstructured":"Wiering MA et al (2000) Multi-agent reinforcement learning for traffic light control. In: Machine learning: proceedings of the seventeenth international conference (ICML\u20192000), pp 1151\u20131158"},{"issue":"1","key":"5197_CR45","doi-asserted-by":"publisher","first-page":"63","DOI":"10.1016\/S0191-2615(01)00045-5","volume":"37","author":"C Wong","year":"2003","unstructured":"Wong C, Wong S (2003) Lane-based optimization of signal timings for isolated junctions. Transportation Research Part B: Methodological 37(1):63\u201384","journal-title":"Transportation Research Part B: Methodological"},{"key":"5197_CR46","doi-asserted-by":"publisher","first-page":"108,304","DOI":"10.1016\/j.knosys.2022.108304","volume":"241","author":"Q Wu","year":"2022","unstructured":"Wu Q, Wu J, Shen J et al (2022) Distributed agent-based deep reinforcement learning for large scale traffic signal control. Knowl-Based Syst 241:108,304","journal-title":"Knowl-Based Syst"},{"key":"5197_CR47","doi-asserted-by":"crossref","unstructured":"Xiong Y, Zheng G, Xu K et al (2019) Learning traffic signal control from demonstrations. In: Proceedings of the 28th ACM international conference on information and knowledge management, pp 2289\u20132292","DOI":"10.1145\/3357384.3358079"},{"issue":"1","key":"5197_CR48","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1080\/15472450.2018.1527694","volume":"24","author":"M Xu","year":"2020","unstructured":"Xu M, Wu J, Huang L et al (2020) Network-wide traffic signal control based on the discovery of critical nodes and deep reinforcement learning. Journal of Intelligent Transportation Systems 24(1):1\u201310","journal-title":"Journal of Intelligent Transportation Systems"},{"issue":"9","key":"5197_CR49","doi-asserted-by":"publisher","first-page":"16,290","DOI":"10.1109\/TITS.2022.3149600","volume":"23","author":"Z Ying","year":"2022","unstructured":"Ying Z, Cao S, Liu X et al (2022) Privacysignal: privacy-preserving traffic signal control for intelligent transportation system. IEEE Trans Intell Transp Syst 23(9):16,290-16,303","journal-title":"IEEE Trans Intell Transp Syst"},{"key":"5197_CR50","doi-asserted-by":"crossref","unstructured":"Zang X, Yao H, Zheng G et al (2020) Metalight: value-based meta-reinforcement learning for traffic signal control. In: Proceedings of the AAAI conference on artificial intelligence, pp 1153\u20131160. https:\/\/aaai.org\/ojs\/index.php\/AAAI\/article\/view\/5467","DOI":"10.1609\/aaai.v34i01.5467"},{"key":"5197_CR51","doi-asserted-by":"crossref","unstructured":"Zhang H, Liu C, Zhang W et al (2020) Generalight: improving environment generalization of traffic signal control via meta reinforcement learning. In: Proceedings of the 29th ACM international conference on information & knowledge management, pp 1783\u20131792","DOI":"10.1145\/3340531.3411859"},{"key":"5197_CR52","doi-asserted-by":"publisher","unstructured":"Zheng G, Xiong Y, Zang X et al (2019) Learning phase competition for traffic signal control. In: Proceedings of the 28th ACM international conference on information and knowledge management, CIKM 2019, Beijing, China. ACM, pp 1963\u20131972. https:\/\/doi.org\/10.1145\/3357384.3357900. Accessed 3-7 Nov 2019","DOI":"10.1145\/3357384.3357900"}],"container-title":["Applied Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-023-05197-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10489-023-05197-w\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-023-05197-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,5]],"date-time":"2024-11-05T00:50:28Z","timestamp":1730767828000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10489-023-05197-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,5]]},"references-count":52,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2024,1]]}},"alternative-id":["5197"],"URL":"https:\/\/doi.org\/10.1007\/s10489-023-05197-w","relation":{},"ISSN":["0924-669X","1573-7497"],"issn-type":[{"value":"0924-669X","type":"print"},{"value":"1573-7497","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,12,5]]},"assertion":[{"value":"24 November 2023","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 December 2023","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}},{"value":"The authors declare that they have no known competing financial interests or personal relationships that could have appeared to influence the work reported in this paper.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}]}}