{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,14]],"date-time":"2026-04-14T22:22:14Z","timestamp":1776205334968,"version":"3.50.1"},"reference-count":47,"publisher":"Springer Science and Business Media LLC","issue":"S2","license":[{"start":{"date-parts":[[2017,6,21]],"date-time":"2017-06-21T00:00:00Z","timestamp":1498003200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Comput & Applic"],"published-print":{"date-parts":[[2019,2]]},"DOI":"10.1007\/s00521-017-3066-9","type":"journal-article","created":{"date-parts":[[2017,6,21]],"date-time":"2017-06-21T04:21:59Z","timestamp":1498018919000},"page":"1013-1028","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":12,"title":["Recursive least-squares temporal difference learning for adaptive traffic signal control at intersection"],"prefix":"10.1007","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8087-5939","authenticated-orcid":false,"given":"Biao","family":"Yin","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mahjoub","family":"Dridi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Abdellah El","family":"Moudni","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2017,6,21]]},"reference":[{"issue":"1","key":"3066_CR1","doi-asserted-by":"publisher","first-page":"42","DOI":"10.1016\/j.arcontrol.2012.03.004","volume":"36","author":"SG Khan","year":"2012","unstructured":"Khan SG, Herrmann G, Lewis FL, Pipe T, Melhuish C (2012) Reinforcement learning and optimal adaptive control: an overview and implementation examples. Annu Rev Control 36(1):42\u201359","journal-title":"Annu Rev Control"},{"key":"3066_CR2","volume-title":"Reinforcement learning: an introduction","author":"RS Sutton","year":"1998","unstructured":"Sutton RS, Barto AG (1998) Reinforcement learning: an introduction. MIT Press, Cambridge"},{"key":"3066_CR3","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.ins.2013.08.037","volume":"261","author":"X Xu","year":"2014","unstructured":"Xu X, Zuo L, Huang Z (2014) Reinforcement learning algorithms with function approximation: recent advances and applications. Inform Sci 261:1\u201331","journal-title":"Inform Sci"},{"key":"3066_CR4","doi-asserted-by":"publisher","DOI":"10.1002\/9780470182963","volume-title":"Approximate dynamic programming: solving the curses of dimensionality","author":"WB Powell","year":"2007","unstructured":"Powell WB (2007) Approximate dynamic programming: solving the curses of dimensionality. Wiley, New York"},{"issue":"2","key":"3066_CR5","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1109\/MCI.2009.932261","volume":"4","author":"FY Wang","year":"2009","unstructured":"Wang FY, Zhang H, Liu D (2009) Adaptive dynamic programming: an introduction. IEEE Comput Intell M 4(2):39\u201347","journal-title":"IEEE Comput Intell M"},{"key":"3066_CR6","first-page":"493","volume":"15","author":"PJ Werbos","year":"1992","unstructured":"Werbos PJ (1992) Approximate dynamic programming for real-time control and neural modeling. Handbook of intelligent control: neural, fuzzy, and adaptive approaches 15:493\u2013525","journal-title":"Handbook of intelligent control: neural, fuzzy, and adaptive approaches"},{"issue":"5","key":"3066_CR7","doi-asserted-by":"publisher","first-page":"456","DOI":"10.1016\/j.trc.2009.04.005","volume":"17","author":"C Cai","year":"2009","unstructured":"Cai C, Wong CK, Heydecker BG (2009) Adaptive traffic signal control using approximate dynamic programming. Transport Res Part C Emerg Technol 17(5):456\u2013474","journal-title":"Transport Res Part C Emerg Technol"},{"issue":"4","key":"3066_CR8","doi-asserted-by":"publisher","first-page":"587","DOI":"10.1017\/S026996480800034X","volume":"22","author":"R Haijema","year":"2008","unstructured":"Haijema R, van der Wal J (2008) An MDP decomposition approach for traffic control at isolated signalized intersections. Proba Eng Inform Sci 22(4):587\u2013602","journal-title":"Proba Eng Inform Sci"},{"issue":"4","key":"3066_CR9","doi-asserted-by":"publisher","first-page":"263","DOI":"10.1016\/j.trc.2006.08.002","volume":"14","author":"XH Yu","year":"2006","unstructured":"Yu XH, Recker WW (2006) Stochastic adaptive control model for traffic signal systems. Transp Res Part C Emerg Technol 14(4):263\u2013282","journal-title":"Transp Res Part C Emerg Technol"},{"key":"3066_CR10","unstructured":"Baird L, Moore AW (1999) Gradient descent for general reinforcement learning. In: Advances in neural information processing systems, pp 968\u2013974"},{"issue":"5","key":"3066_CR11","doi-asserted-by":"publisher","first-page":"674","DOI":"10.1109\/9.580874","volume":"42","author":"JN Tsitsiklis","year":"1997","unstructured":"Tsitsiklis JN, Van Roy B (1997) An analysis of temporal-difference learning with function approximation. IEEE Trans Automat Contr 42(5):674\u2013690","journal-title":"IEEE Trans Automat Contr"},{"issue":"1","key":"3066_CR12","doi-asserted-by":"publisher","first-page":"259","DOI":"10.1613\/jair.946","volume":"16","author":"X Xu","year":"2002","unstructured":"Xu X, He H, Hu D (2002) Efficient reinforcement learning using recursive least-squares methods. J Artif Intell Res 16(1):259\u2013292","journal-title":"J Artif Intell Res"},{"issue":"2\u20133","key":"3066_CR13","doi-asserted-by":"publisher","first-page":"161","DOI":"10.1023\/A:1017928328829","volume":"49","author":"D Ormoneit","year":"2002","unstructured":"Ormoneit D, Sen \u015a (2002) Kernel-based reinforcement learning. Mach Learn 49(2\u20133):161\u2013178","journal-title":"Mach Learn"},{"issue":"1\u20133","key":"3066_CR14","first-page":"33","volume":"22","author":"SJ Bradtke","year":"1996","unstructured":"Bradtke SJ, Barto AG (1996) Linear least-squares algorithms for temporal difference learning. Mach Learn 22(1\u20133):33\u201357","journal-title":"Mach Learn"},{"issue":"2\u20133","key":"3066_CR15","doi-asserted-by":"publisher","first-page":"233","DOI":"10.1023\/A:1017936530646","volume":"49","author":"JA Boyan","year":"2002","unstructured":"Boyan JA (2002) Technical update: least-squares temporal difference learning. Mach Learn 49(2\u20133):233\u2013246","journal-title":"Mach Learn"},{"key":"3066_CR16","unstructured":"Hunt PB, Robertson DI, Bretherton RD, Winton RI (1981) SCOOT\u2013a traffic responsive method of coordinating signals. Transport and Road Research Laboratory, Crowthorne, Technique Report"},{"key":"3066_CR17","unstructured":"Lowrie PR (1982) The Sydney coordinated adaptive traffic system-principles, methodology, algorithms. In: Proceddings of international conference on road traffic signalling"},{"key":"3066_CR18","unstructured":"Mladenovic MN, Stevanovic A, Kosonen I, Glavic D (2015) Adaptive traffic control systems: guidelines for development of functional requirements. mobil.TUM. Munich, Germany"},{"key":"3066_CR19","doi-asserted-by":"crossref","unstructured":"Gartner NH, Pooran FJ, Andrews CM (2001) Implementation of the OPAC adaptive control strategy in a traffic signal network. In: Proceedings of IEEE conference intelligent transportation systems, pp 195\u2013200","DOI":"10.1109\/ITSC.2001.948655"},{"key":"3066_CR20","doi-asserted-by":"crossref","unstructured":"Henry J, Farges J, Tuffal J (1984) The PRODYN real time traffic algorithm. IFACIFIP-IFORS conference on control in transportation system. \n                    http:\/\/trid.trb.org\/view.aspx?id=339694","DOI":"10.1016\/B978-0-08-029365-3.50048-1"},{"issue":"6","key":"3066_CR21","doi-asserted-by":"publisher","first-page":"415","DOI":"10.1016\/S0968-090X(00)00047-4","volume":"9","author":"P Mirchandani","year":"2001","unstructured":"Mirchandani P, Head L (2001) A real-time traffic signal control system: architecture, algorithms, and analysis. Transp Res Part C Emerg Technol 9(6):415\u2013432","journal-title":"Transp Res Part C Emerg Technol"},{"issue":"3","key":"3066_CR22","doi-asserted-by":"publisher","first-page":"341","DOI":"10.1109\/TITS.2005.853713","volume":"6","author":"TH Heung","year":"2005","unstructured":"Heung TH, Ho TK, Fung YF (2005) Coordinated road-junction traffic control by dynamic programming. IEEE Trans Intell Transp 6(3):341\u2013350","journal-title":"IEEE Trans Intell Transp"},{"key":"3066_CR23","doi-asserted-by":"crossref","unstructured":"Wu J, Abbas-Turki A, El Moudni A (2009) Discrete methods for urban intersection traffic controlling. In Proceedings of IEEE vehicular technology conference, pp 1\u20135","DOI":"10.1109\/VETECS.2009.5073497"},{"key":"3066_CR24","doi-asserted-by":"publisher","first-page":"115","DOI":"10.3141\/1811-14","volume":"1811","author":"B Park","year":"2002","unstructured":"Park B, Chang M (2002) Realizing benefits of adaptive signal control at an isolated intersection. Transport Res Rec 1811:115\u2013121","journal-title":"Transport Res Rec"},{"issue":"3","key":"3066_CR25","doi-asserted-by":"publisher","first-page":"278","DOI":"10.1061\/(ASCE)0733-947X(2003)129:3(278)","volume":"129","author":"B Abdulhai","year":"2003","unstructured":"Abdulhai B, Pringle R, Karakoulas GJ (2003) Reinforcement learning for true adaptive traffic signal control. J Transp Eng-ASCE 129(3):278\u2013285","journal-title":"J Transp Eng-ASCE"},{"issue":"3","key":"3066_CR26","doi-asserted-by":"publisher","first-page":"111","DOI":"10.1080\/15472450500183649","volume":"9","author":"J Lee","year":"2005","unstructured":"Lee J, Abdulhai B, Shalaby A, Chung EH (2005) Real-time optimization for adaptive traffic signal control using genetic algorithms. J Intell Transport S 9(3):111\u2013122","journal-title":"J Intell Transport S"},{"issue":"2","key":"3066_CR27","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1080\/15472451003719764","volume":"14","author":"C Kergaye","year":"2010","unstructured":"Kergaye C, Stevanovic A, Martin PT (2010) Comparative evaluation of adaptive traffic control system assessments through field and microsimulation. J Intell Transport S 14(2):109\u2013124","journal-title":"J Intell Transport S"},{"issue":"3","key":"3066_CR28","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 J Autom Sin 3(3):247\u2013254","journal-title":"IEEE\/CAA J Autom Sin"},{"issue":"3","key":"3066_CR29","doi-asserted-by":"publisher","first-page":"1538","DOI":"10.1016\/j.eswa.2014.09.003","volume":"42","author":"S Araghi","year":"2015","unstructured":"Araghi S, Khosravi A, Creighton D (2015) A review on computational intelligence methods for controlling traffic signal timing. Expert Syst Appl 42(3):1538\u20131550","journal-title":"Expert Syst Appl"},{"issue":"2","key":"3066_CR30","doi-asserted-by":"publisher","first-page":"274","DOI":"10.1016\/j.engappai.2011.04.011","volume":"25","author":"J Garc\u00eda-Nieto","year":"2012","unstructured":"Garc\u00eda-Nieto J, Alba E, Carolina Olivera A (2012) Swarm intelligence for traffic light scheduling: application to real urban areas. Eng Appl Artif Intell 25(2):274\u2013283","journal-title":"Eng Appl Artif Intell"},{"issue":"3","key":"3066_CR31","doi-asserted-by":"publisher","first-page":"261","DOI":"10.1109\/TITS.2006.874716","volume":"7","author":"D Srinivasan","year":"2006","unstructured":"Srinivasan D, Choy MC, Cheu RL (2006) Neural networks for real-time traffic signal control. IEEE Trans Intell Transp 7(3):261\u2013272","journal-title":"IEEE Trans Intell Transp"},{"issue":"2","key":"3066_CR32","doi-asserted-by":"publisher","first-page":"128","DOI":"10.1049\/iet-its.2009.0070","volume":"4","author":"I Arel","year":"2010","unstructured":"Arel I, Liu C, Urbanik T, Kohls AG (2010) Reinforcement learning-based multi-agent system for network traffic signal control. IET Intell Transp Syst 4(2):128\u2013135","journal-title":"IET Intell Transp Syst"},{"issue":"3","key":"3066_CR33","doi-asserted-by":"publisher","first-page":"342","DOI":"10.1007\/s10458-008-9062-9","volume":"18","author":"ALC Bazzan","year":"2009","unstructured":"Bazzan ALC (2009) Opportunities for multiagent systems and multiagent reinforcement learning in traffic control. Auton Agent Multi-Agent Syst 18(3):342\u2013375","journal-title":"Auton Agent Multi-Agent Syst"},{"issue":"1","key":"3066_CR34","doi-asserted-by":"publisher","first-page":"652","DOI":"10.1016\/j.engappai.2012.02.013","volume":"26","author":"S Box","year":"2013","unstructured":"Box S, Waterson B (2013) An automated signalized junction controller that learns strategies by temporal difference reinforcement learning. Eng Appl Artif Intell 26(1):652\u2013659","journal-title":"Eng Appl Artif Intell"},{"issue":"2","key":"3066_CR35","doi-asserted-by":"publisher","first-page":"412","DOI":"10.1109\/TITS.2010.2091408","volume":"12","author":"LA Prashanth","year":"2011","unstructured":"Prashanth LA, Bhatnagar S (2011) Reinforcement learning with function approximation for traffic signal control. IEEE Trans Intell Transp 12(2):412\u2013421","journal-title":"IEEE Trans Intell Transp"},{"issue":"3","key":"3066_CR36","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 14(3):1140\u20131150","journal-title":"IEEE Trans Intell Transp"},{"key":"3066_CR37","doi-asserted-by":"crossref","unstructured":"Li T, Zhao D, Yi J (2008) Adaptive dynamic programming for multi-intersections traffic signal intelligent control. In: Proceedings of IEEE conference intelligent transportation systems, pp 286\u2013291","DOI":"10.1109\/ITSC.2008.4732718"},{"key":"3066_CR38","doi-asserted-by":"publisher","first-page":"57","DOI":"10.1016\/j.neucom.2012.09.034","volume":"125","author":"D Zhao","year":"2014","unstructured":"Zhao D, Hu Z, Xia Z, Alippi C, Zhu Y, Wang D (2014) Full-range adaptive cruise control based on supervised adaptive dynamic programming. Neurocomputing 125:57\u201367","journal-title":"Neurocomputing"},{"issue":"2","key":"3066_CR39","doi-asserted-by":"publisher","first-page":"530","DOI":"10.1109\/TITS.2013.2283034","volume":"15","author":"YS Huang","year":"2014","unstructured":"Huang YS, Weng YS, Zhou MC (2014) Modular design of urban traffic-light control systems based on synchronized timed Petri nets. IEEE Trans Intell Transp 15(2):530\u2013539","journal-title":"IEEE Trans Intell Transp"},{"issue":"3","key":"3066_CR40","doi-asserted-by":"publisher","first-page":"227","DOI":"10.1080\/15472450.2013.810991","volume":"18","author":"S El-Tantawy","year":"2014","unstructured":"El-Tantawy S, Abdulhai B, Abdelgawad H (2014) Design of reinforcement learning parameters for seamless application of adaptive traffic signal control. J Intell Transp Syst 18(3):227\u2013245","journal-title":"J Intell Transp Syst"},{"issue":"2","key":"3066_CR41","doi-asserted-by":"publisher","first-page":"156","DOI":"10.1109\/TSMCC.2007.913919","volume":"38","author":"L Busoniu","year":"2008","unstructured":"Busoniu L, Babuska R, De Schutter B (2008) A comprehensive survey of multiagent reinforcement learning. IEEE Trans Syst Man Cybern C 38(2):156\u2013172","journal-title":"IEEE Trans Syst Man Cybern C"},{"key":"3066_CR42","unstructured":"Bertsekas DP (1995) Dynamic programming and optimal control vol. 1 No 2. Athena Scientific, Belmont"},{"key":"3066_CR43","first-page":"105","volume":"1324","author":"NH Gartner","year":"1991","unstructured":"Gartner NH, Tarnoff PJ, Andrews CM (1991) Evaluation of optimized policies for adaptive control strategy. Transp Res Rec 1324:105\u2013114","journal-title":"Transp Res Rec"},{"issue":"7","key":"3066_CR44","doi-asserted-by":"publisher","first-page":"754","DOI":"10.1049\/iet-its.2014.0156","volume":"9","author":"B Yin","year":"2015","unstructured":"Yin B, Dridi M, El Moudni A (2015) Forward search algorithm based on dynamic programming for real-time adaptive traffic signal control. IET Intell Transp Syst 9(7):754\u2013764","journal-title":"IET Intell Transp Syst"},{"key":"3066_CR45","unstructured":"Khamis MA, Gomaa W (2012) Enhanced multiagent multi-objective reinforcement learning for urban traffic light control. In: Proceedings of IEEE conference machine learning and applications, pp 586\u2013591"},{"key":"3066_CR46","doi-asserted-by":"publisher","first-page":"134","DOI":"10.1016\/j.engappai.2014.01.007","volume":"29","author":"MA Khamis","year":"2014","unstructured":"Khamis MA, Gomaa W (2014) Adaptive multi-objective reinforcement learning with hybrid exploration for traffic signal control based on cooperative multi-agent framework. Eng Appl Artif Intell 29:134\u2013151","journal-title":"Eng Appl Artif Intell"},{"issue":"1","key":"3066_CR47","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/BF01211647","volume":"21","author":"T S\u00f6derstr\u00f6m","year":"2002","unstructured":"S\u00f6derstr\u00f6m T, Stoica P (2002) Instrumental variable methods for system identification. Circ Syst Signal Process 21(1):1\u20139","journal-title":"Circ Syst Signal Process"}],"container-title":["Neural Computing and Applications"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-017-3066-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s00521-017-3066-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-017-3066-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,8,28]],"date-time":"2019-08-28T10:31:43Z","timestamp":1566988303000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s00521-017-3066-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,6,21]]},"references-count":47,"journal-issue":{"issue":"S2","published-print":{"date-parts":[[2019,2]]}},"alternative-id":["3066"],"URL":"https:\/\/doi.org\/10.1007\/s00521-017-3066-9","relation":{},"ISSN":["0941-0643","1433-3058"],"issn-type":[{"value":"0941-0643","type":"print"},{"value":"1433-3058","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017,6,21]]},"assertion":[{"value":"21 December 2016","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 June 2017","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 June 2017","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Compliance with ethical standards"}},{"value":"The authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}