{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T20:10:50Z","timestamp":1773778250965,"version":"3.50.1"},"reference-count":40,"publisher":"American Society of Civil Engineers (ASCE)","issue":"1","content-domain":{"domain":["ascelibrary.org"],"crossmark-restriction":true},"short-container-title":["J. Comput. Civ. Eng."],"published-print":{"date-parts":[[2020,1]]},"DOI":"10.1061\/(asce)cp.1943-5487.0000859","type":"journal-article","created":{"date-parts":[[2019,10,22]],"date-time":"2019-10-22T13:21:01Z","timestamp":1571750461000},"update-policy":"https:\/\/doi.org\/10.1061\/do.news.20190416.0001","source":"Crossref","is-referenced-by-count":22,"title":["Policy Analysis of Adaptive Traffic Signal Control Using Reinforcement Learning"],"prefix":"10.1061","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9844-8652","authenticated-orcid":true,"given":"Wade","family":"Genders","sequence":"first","affiliation":[{"name":"Ph.D. Student, Dept. of Civil Engineering, McMaster Univ., 1280 Main St. West, Hamilton, ON, Canada L8S 4L8 (corresponding author). ORCID: ."}]},{"given":"Saiedeh","family":"Razavi","sequence":"additional","affiliation":[{"name":"Associate Professor, Dept. of Civil Engineering, McMaster Univ., 1280 Main St. West, Hamilton, ON, Canada L8S 4L8."}]}],"member":"30","reference":[{"key":"e_1_3_2_2_1","unstructured":"Abadi M. et al. 2016. \u201cTensorflow: Large-scale machine learning on heterogeneous distributed systems.\u201d Preprint submitted March 14 2016. http:\/\/arxiv.org\/abs\/1603.04467."},{"key":"e_1_3_2_3_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2013.01.007"},{"key":"e_1_3_2_4_1","doi-asserted-by":"publisher","DOI":"10.1061\/(ASCE)0733-947X(2003)129:3(278)"},{"key":"e_1_3_2_5_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2017.09.020"},{"key":"e_1_3_2_6_1","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.64.056132"},{"key":"e_1_3_2_7_1","unstructured":"Casas N. 2017. \u201cDeep deterministic policy gradient for urban traffic light control.\u201d Preprint submitted March 27 2017. http:\/\/arxiv.org\/abs\/1703.09035."},{"key":"e_1_3_2_8_1","doi-asserted-by":"crossref","unstructured":"Chun-Gui L. W. Meng S. Zi-Gaung L. Fei-Ying and Z. Zeng-Fang. 2009. \u201cUrban traffic signal learning control using fuzzy actor-critic methods.\u201d In Vol. 1 of Proc. 5th Int. Conf. on Natural Computation 2009 (ICNC\u201909) 368\u2013372. New York: IEEE.","DOI":"10.1109\/ICNC.2009.374"},{"key":"e_1_3_2_9_1","unstructured":"City of Toronto. 2018a. \u201cTraffic signal operations policies and strategies.\u201d Accessed April 29 2018. https:\/\/www.toronto.ca\/services-payments\/streets-parking-transportation\/traffic-management\/traffic-signals-street-signs\/signal-policies-and-coordination\/."},{"key":"e_1_3_2_10_1","unstructured":"City of Toronto. 2018b. \u201cTraffic signals\u2014Operation\u2014Timing.\u201d Accessed April 26 2018. https:\/\/www.toronto.ca\/services-payments\/streets-parking-transportation\/traffic-management\/traffic-signals-street-signs\/signal-policies-and-coordination\/."},{"key":"e_1_3_2_11_1","unstructured":"Cs\u00e1ji B. C. 2001. \u201cApproximation with artificial neural networks.\u201d M.Sc. thesis Faculty of Sciences Etvs Lornd Univ."},{"key":"e_1_3_2_12_1","doi-asserted-by":"crossref","unstructured":"Degris T. P. M. Pilarski and R. S. Sutton. 2012. \u201cModel-free reinforcement learning with continuous action in practice.\u201d In Proc. American Control Conf. (ACC) 2177\u20132182. New York: IEEE.","DOI":"10.1109\/ACC.2012.6315022"},{"key":"e_1_3_2_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2013.2255286"},{"key":"e_1_3_2_14_1","doi-asserted-by":"publisher","DOI":"10.1080\/15472450.2013.810991"},{"key":"e_1_3_2_15_1","unstructured":"Fernando C. D. Banarse C. Blundell Y. Zwols D. Ha A. A. Rusu A. Pritzel and D. Wierstra. 2017. \u201cPathnet: Evolution channels gradient descent in super neural networks.\u201d Preprint submitted January 30 2017. http:\/\/arxiv.org\/abs\/1701.08734."},{"key":"e_1_3_2_16_1","unstructured":"Genders W. and S. Razavi. 2016. \u201cUsing a deep reinforcement learning agent for traffic signal control.\u201d Preprint submitted November 3 2016. http:\/\/arxiv.org\/abs\/1611.01142."},{"key":"e_1_3_2_17_1","unstructured":"Goel S. S. F. Bush and C. Gershenson. 2017. \u201cSelf-organization in traffic lights: Evolution of signal control with advances in sensors and communications.\u201d Preprint submitted June 18 2017. http:\/\/arxiv.org\/abs\/1708.07188."},{"key":"e_1_3_2_18_1","unstructured":"Higgins I. A. Pal A. A. Rusu L. Matthey C. P. Burgess A. Pritzel M. Botvinick C. Blundell and A. Lerchner. 2017. \u201cDarla: Improving zero-shot transfer in reinforcement learning.\u201d Preprint submitted July 26 2017. http:\/\/arxiv.org\/abs\/1707.08475."},{"key":"e_1_3_2_19_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2017.07.022"},{"key":"e_1_3_2_20_1","unstructured":"Jones E. E. Oliphant and P. Peterson. 2001. \u201cSciPy: Open source scientific tools for Python.\u201d Accessed September 30 2019. http:\/\/www.scipy.org\/."},{"key":"e_1_3_2_21_1","unstructured":"Kapturowski S. 2017. \u201cTensorflow-rl.\u201d Accessed September 14 2017. https:\/\/github.com\/steveKapturowski\/tensorflow-rl."},{"key":"e_1_3_2_22_1","unstructured":"Kingma D. and J. Ba. 2014. \u201cAdam: A method for stochastic optimization.\u201d Preprint submitted December 22 2014. http:\/\/arxiv.org\/abs\/1412.6980."},{"issue":"3","key":"e_1_3_2_23_1","first-page":"128","article-title":"Recent development and applications of SUMO: Simulation of urban mobility","volume":"5","author":"Krajzewicz D.","year":"2012","journal-title":"Int. J. Adv. Syst. Meas."},{"key":"e_1_3_2_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2016.7508798"},{"key":"e_1_3_2_25_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-25808-9_4"},{"key":"e_1_3_2_26_1","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"e_1_3_2_27_1","unstructured":"Mnih V. A. P. Badia M. Mirza A. Graves T. Lillicrap T. Harley D. Silver and K. Kavukcuoglu. 2016. \u201cAsynchronous methods for deep reinforcement learning.\u201d In Proc. Int. Conf. on Machine Learning 1928\u20131937. Brookline MA: Microtome Publishing."},{"key":"e_1_3_2_28_1","unstructured":"Mousavi S. S. M. Schukat P. Corcoran and E. Howley. 2017. \u201cTraffic light control using deep policy-gradient and value-function based reinforcement learning.\u201d Preprint submitted April 28 2017. http:\/\/arxiv.org\/abs\/1704.08883."},{"key":"e_1_3_2_29_1","doi-asserted-by":"crossref","unstructured":"Peters J. Vijayakumar S. and Schaal S. 2005. \u201cNatural actor-critic.\u201d In Proc. European Conf. on Machine Learning 280\u2013291. New York: Springer.","DOI":"10.1007\/11564096_29"},{"key":"e_1_3_2_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2010.2091408"},{"key":"e_1_3_2_31_1","doi-asserted-by":"crossref","unstructured":"Richter S. D. Aberdeen and J. Yu. 2007. \u201cNatural actor-critic for road traffic optimisation.\u201d In Proc. Advances in Neural Information Processing Systems 1169\u20131176. Red Hook NY: Curran Associates .","DOI":"10.7551\/mitpress\/7503.003.0151"},{"key":"e_1_3_2_32_1","unstructured":"Rijken T. 2015. \u201cDeeplight: Deep reinforcement learning for signalised traffic control.\u201d Master\u2019s thesis Dept. of Computer Science Faculty of Engineering Sciences Univ. College London."},{"key":"e_1_3_2_33_1","doi-asserted-by":"publisher","DOI":"10.1038\/323533a0"},{"key":"e_1_3_2_34_1","unstructured":"Sharma S. A. S. Lakshminarayanan and B. Ravindran. 2017. \u201cLearning to repeat: Fine grained action repetition for deep reinforcement learning.\u201d Preprint submitted February 20 2017. http:\/\/arxiv.org\/abs\/1702.06054."},{"key":"e_1_3_2_35_1","volume-title":"Reinforcement learning: An introduction","author":"Sutton R. S.","year":"1998"},{"key":"e_1_3_2_37_1","unstructured":"van der Pol E. 2016. \u201cDeep reinforcement learning for coordination in traffic light control.\u201d Master\u2019s thesis Dept. of Mathematics and Computer Science Faculty of Natural Sciences Univ. of Amsterdam."},{"key":"e_1_3_2_38_1","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"e_1_3_2_40_1","unstructured":"Wiering M. 2000. \u201cMulti-agent reinforcement learning for traffic light control.\u201d In Proc. 17th Int. Conf. on Machine Learning 1151\u20131158. New York: IEEE."},{"key":"e_1_3_2_41_1","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"e_1_3_2_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3068287"},{"key":"e_1_3_2_43_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2014.12.009"}],"container-title":["Journal of Computing in Civil Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/ascelibrary.org\/doi\/pdf\/10.1061\/%28ASCE%29CP.1943-5487.0000859","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,21]],"date-time":"2023-09-21T23:39:21Z","timestamp":1695339561000},"score":1,"resource":{"primary":{"URL":"https:\/\/ascelibrary.org\/doi\/10.1061\/%28ASCE%29CP.1943-5487.0000859"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,1]]},"references-count":40,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2020,1]]}},"alternative-id":["10.1061\/(ASCE)CP.1943-5487.0000859"],"URL":"https:\/\/doi.org\/10.1061\/(asce)cp.1943-5487.0000859","relation":{},"ISSN":["0887-3801","1943-5487"],"issn-type":[{"value":"0887-3801","type":"print"},{"value":"1943-5487","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,1]]},"assertion":[{"value":"2018-11-21","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2019-04-10","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2019-10-22","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"04019046"}}