{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,8,16]],"date-time":"2024-08-16T15:48:59Z","timestamp":1723823339574},"reference-count":34,"publisher":"Springer Science and Business Media LLC","issue":"10","license":[{"start":{"date-parts":[[2023,4,25]],"date-time":"2023-04-25T00:00:00Z","timestamp":1682380800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,4,25]],"date-time":"2023-04-25T00:00:00Z","timestamp":1682380800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int. J. Mach. Learn. & Cyber."],"published-print":{"date-parts":[[2023,10]]},"DOI":"10.1007\/s13042-023-01838-1","type":"journal-article","created":{"date-parts":[[2023,4,25]],"date-time":"2023-04-25T09:02:43Z","timestamp":1682413363000},"page":"3381-3391","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Optimizing traffic efficiency via a reinforcement learning approach based on time allocation"],"prefix":"10.1007","volume":"14","author":[{"given":"Chao","family":"Xiang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhongming","family":"Jin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhengxu","family":"Yu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xian-Sheng","family":"Hua","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yao","family":"Hu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Qian","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kaili","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Deng","family":"Cai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaofei","family":"He","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,4,25]]},"reference":[{"key":"1838_CR1","unstructured":"Schneider B (2018) Traffic\u2019s mind-boggling economic toll. Accessed 7 February 2018. https:\/\/www.citylab.com\/transportation\/2018\/02\/traffics-mind-boggling-economic-toll\/552488\/"},{"key":"1838_CR2","unstructured":"Burfeind M (2018) Traffic congestion cost UK motorists over \u00a3$$37.7$$ billion in 2017. Accessed 5 Feb 2018. http:\/\/inrix.com\/press-releases\/scorecard-2017-uk\/"},{"key":"1838_CR3","unstructured":"Smith SF, Barlow G, Xie X-F, Rubinstein ZB (2013) Surtrac: scalable urban traffic control"},{"key":"1838_CR4","doi-asserted-by":"crossref","unstructured":"Chin S-M, Franzese O, Greene DL, Hwang H-L, Gibson R et al (2004) Temporary losses of highway capacity and impacts on performance: Phase 2. United States. Dept. of Energy. Office of Scientific and Technical Information","DOI":"10.2172\/885576"},{"key":"1838_CR5","unstructured":"Webster FV (1958) Traffic signal settings. Technical report"},{"issue":"4","key":"1838_CR6","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. J Oper Res Soc 14(4):373\u2013386","journal-title":"J Oper Res Soc"},{"issue":"3\u20134","key":"1838_CR7","first-page":"209","volume":"4","author":"I Porche","year":"1999","unstructured":"Porche I, Lafortune S (1999) Adaptive look-ahead optimization of traffic signals. J Intell Trans Syst 4(3\u20134):209\u2013254","journal-title":"J Intell Trans Syst"},{"key":"1838_CR8","doi-asserted-by":"crossref","unstructured":"Cools SB, Gershenson C, D\u2019Hooghe B (2013) Self-organizing traffic lights: A realistic simulation. Advances in applied self-organizing systems 45\u201355","DOI":"10.1007\/978-1-4471-5113-5_3"},{"key":"1838_CR9","unstructured":"Sutton RS, Barto AG (2018) Reinforcement Learning: An Introduction. MIT press"},{"key":"1838_CR10","doi-asserted-by":"publisher","first-page":"956","DOI":"10.1016\/j.procs.2015.05.172","volume":"52","author":"P Mannion","year":"2015","unstructured":"Mannion P, Duggan J, Howley E (2015) Parallel reinforcement learning for traffic signal control. Proc Comput Sci 52:956\u2013961","journal-title":"Proc Comput Sci"},{"key":"1838_CR11","doi-asserted-by":"publisher","first-page":"513","DOI":"10.1016\/j.procs.2017.05.327","volume":"109","author":"S Touhbi","year":"2017","unstructured":"Touhbi S, Babram MA, Nguyen-Huu T, Marilleau N, Hbid ML, Cambier C, Stinckwich S (2017) Adaptive traffic signal control: Exploring reward definition for reinforcement learning. Proc Comput Sci 109:513\u2013520","journal-title":"Proc Comput Sci"},{"key":"1838_CR12","doi-asserted-by":"crossref","unstructured":"Kuyer L, Whiteson S, Bakker B, Vlassis N (2008) Multiagent reinforcement learning for urban traffic control using coordination graphs. In: Joint European Conference on Machine Learning and Knowledge Discovery in Databases, pp. 656\u2013671. Springer","DOI":"10.1007\/978-3-540-87479-9_61"},{"issue":"3","key":"1838_CR13","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 Trans Syst 14(3):1140\u20131150","journal-title":"IEEE Trans Intell Trans Syst"},{"issue":"7540","key":"1838_CR14","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1038\/nature14236","volume":"518","author":"V Mnih","year":"2015","unstructured":"Mnih V, Kavukcuoglu K, Silver D, Rusu AA, Veness J, Bellemare MG, Graves A, Riedmiller M, Fidjeland AK, Ostrovski G et al (2015) Human-level control through deep reinforcement learning. Nature 518(7540):529","journal-title":"Nature"},{"issue":"7676","key":"1838_CR15","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, Antonoglou I, Huang A, Guez A, Hubert T, Baker L, Lai M, Bolton A et al (2017) Mastering the game of go without human knowledge. Nature 550(7676):354","journal-title":"Nature"},{"key":"1838_CR16","unstructured":"Genders W, Razavi S (2016) Using a deep reinforcement learning agent for traffic signal control. arXiv preprint arXiv:1611.01142"},{"key":"1838_CR17","unstructured":"Gao J, Shen Y, Liu J, Ito M, Shiratori N (2017) Adaptive traffic signal control: Deep reinforcement learning algorithm with experience replay and target network. arXiv preprint arXiv:1705.02755"},{"key":"1838_CR18","unstructured":"Van\u00a0der 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)"},{"key":"1838_CR19","doi-asserted-by":"crossref","unstructured":"Wei H, Zheng G, Yao H, Li Z (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, pp. 2496\u20132505. ACM","DOI":"10.1145\/3219819.3220096"},{"key":"1838_CR20","doi-asserted-by":"publisher","unstructured":"Zhao J, Guan Z, Xu C, Zhao W, Chen E (2022) Charge prediction by constitutive elements matching of crimes. In: Raedt, L.D. (ed.) Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence, IJCAI 22, (23\u201329):4517\u20134523. https:\/\/doi.org\/10.24963\/ijcai.2022\/627","DOI":"10.24963\/ijcai.2022\/627"},{"key":"1838_CR21","doi-asserted-by":"crossref","unstructured":"Guan Z, Wu H, Cao Q, Liu H, Zhao W, Li S, Xu C, Qiu G, Xu J, Zheng B (2021) Multi-agent cooperative bidding games for multi-objective optimization in e-commercial sponsored search. In: Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining, pp. 2899\u20132909","DOI":"10.1145\/3447548.3467204"},{"key":"1838_CR22","doi-asserted-by":"crossref","unstructured":"Zhao J, Qiu G, Guan Z, Zhao W, He X (2018) Deep reinforcement learning for sponsored search real-time bidding. In: Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp. 1021\u20131030","DOI":"10.1145\/3219819.3219918"},{"key":"1838_CR23","unstructured":"Watkins CJCH (1989) Learning form delayed rewards. PhD thesis, King\u2019s College, University of Cambridge"},{"key":"1838_CR24","doi-asserted-by":"crossref","unstructured":"Yang Y, Guan Z, Li J, Zhao W, Cui J, Wang Q (2021) Interpretable and efficient heterogeneous graph convolutional network. IEEE Trans Knowl Data Eng","DOI":"10.1109\/TKDE.2021.3101356"},{"issue":"2","key":"1838_CR25","doi-asserted-by":"publisher","first-page":"563","DOI":"10.1109\/TPAMI.2019.2932058","volume":"44","author":"J Yu","year":"2019","unstructured":"Yu J, Tan M, Zhang H, Rui Y, Tao D (2019) Hierarchical deep click feature prediction for fine-grained image recognition. IEEE Trans Pattern Anal Mach Intell 44(2):563\u2013578","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"12","key":"1838_CR26","doi-asserted-by":"publisher","first-page":"5659","DOI":"10.1109\/TIP.2015.2487860","volume":"24","author":"C Hong","year":"2015","unstructured":"Hong C, Yu J, Wan J, Tao D, Wang M (2015) Multimodal deep autoencoder for human pose recovery. IEEE Trans Image Process 24(12):5659\u20135670","journal-title":"IEEE Trans Image Process"},{"issue":"6","key":"1838_CR27","doi-asserted-by":"publisher","first-page":"1789","DOI":"10.1007\/s13042-021-01274-z","volume":"12","author":"T Ye","year":"2021","unstructured":"Ye T, Zhang Z, Zhang X, Chen Y, Zhou F (2021) Fault detection of railway freight cars mechanical components based on multi-feature fusion convolutional neural network. Int J Mach Learn Cybernet 12(6):1789\u20131801","journal-title":"Int J Mach Learn Cybernet"},{"issue":"12","key":"1838_CR28","doi-asserted-by":"publisher","first-page":"2849","DOI":"10.1007\/s13042-020-01155-x","volume":"11","author":"S Liu","year":"2020","unstructured":"Liu S, Li T, Ding H, Tang B, Wang X, Chen Q, Yan J, Zhou Y (2020) A hybrid method of recurrent neural network and graph neural network for next-period prescription prediction. Int J Mach Learn Cybernet 11(12):2849\u20132856","journal-title":"Int J Mach Learn Cybernet"},{"issue":"7","key":"1838_CR29","doi-asserted-by":"publisher","first-page":"3952","DOI":"10.1109\/TII.2018.2884211","volume":"15","author":"C Hong","year":"2018","unstructured":"Hong C, Yu J, Zhang J, Jin X, Lee K-H (2018) Multimodal face-pose estimation with multitask manifold deep learning. IEEE Trans Ind Inform 15(7):3952\u20133961","journal-title":"IEEE Trans Ind Inform"},{"key":"1838_CR30","unstructured":"Lillicrap TP, Hunt JJ, Pritzel A, Heess N, Erez T, Tassa Y, Silver D, Wierstra D (2015) Continuous control with deep reinforcement learning. arXiv preprint arXiv:1509.02971"},{"key":"1838_CR31","unstructured":"Gu S, Lillicrap T, Sutskever I, Levine S (2016) Continuous deep q-learning with model-based acceleration. In: International Conference on Machine Learning, pp. 2829\u20132838"},{"issue":"11","key":"1838_CR32","doi-asserted-by":"publisher","first-page":"2278","DOI":"10.1109\/5.726791","volume":"86","author":"Y LeCun","year":"1998","unstructured":"LeCun Y, Bottou L, Bengio Y, Haffner P (1998) Gradient-based learning applied to document recognition. Proc IEEE 86(11):2278\u20132324","journal-title":"Proc IEEE"},{"key":"1838_CR33","unstructured":"Nair V, Hinton GE (2010) Rectified linear units improve restricted boltzmann machines. In: Proceedings of the 27th international conference on machine learning (ICML-10), pp. 807\u2013814"},{"issue":"3 &4","key":"1838_CR34","first-page":"128","volume":"5","author":"D Krajzewicz","year":"2012","unstructured":"Krajzewicz D, Erdmann J, Behrisch M, Bieker L (2012) Recent development and applications of SUMO\u2014simulation of Urban MObility. Int J Adv Syst Measure 5(3 &4):128\u2013138","journal-title":"Int J Adv Syst Measure"}],"container-title":["International Journal of Machine Learning and Cybernetics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13042-023-01838-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s13042-023-01838-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13042-023-01838-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,22]],"date-time":"2023-08-22T05:24:27Z","timestamp":1692681867000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s13042-023-01838-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,4,25]]},"references-count":34,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2023,10]]}},"alternative-id":["1838"],"URL":"https:\/\/doi.org\/10.1007\/s13042-023-01838-1","relation":{},"ISSN":["1868-8071","1868-808X"],"issn-type":[{"value":"1868-8071","type":"print"},{"value":"1868-808X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,4,25]]},"assertion":[{"value":"25 November 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 April 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 April 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"This work was supported in part by The National Key Research and Development Program of China (Grant Nos: 2018AAA0101400), in part by The National Nature Science Foundation of China (Grant Nos: 62036009, U1909203, 61936006), in part by Innovation Capability Support Program of Shaanxi (Program No. 2021TD-05).","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Funding"}},{"value":"The authors have no competing interests to declare that are relevant to the content of this article.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}