{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,3]],"date-time":"2026-10-03T17:27:43Z","timestamp":1791048463496,"version":"4.1.0"},"reference-count":60,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2023,8,1]],"date-time":"2023-08-01T00:00:00Z","timestamp":1690848000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,8,1]],"date-time":"2023-08-01T00:00:00Z","timestamp":1690848000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,8,1]],"date-time":"2023-08-01T00:00:00Z","timestamp":1690848000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2018AAA0101100"],"award-info":[{"award-number":["2018AAA0101100"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62073160"],"award-info":[{"award-number":["62073160"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Comput. Soc. Syst."],"published-print":{"date-parts":[[2023,8]]},"DOI":"10.1109\/tcss.2022.3225362","type":"journal-article","created":{"date-parts":[[2022,12,5]],"date-time":"2022-12-05T22:47:18Z","timestamp":1670280438000},"page":"1997-2007","source":"Crossref","is-referenced-by-count":20,"title":["Extracting Decision Tree From Trained Deep Reinforcement Learning in Traffic Signal Control"],"prefix":"10.1109","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7484-1804","authenticated-orcid":false,"given":"Yuanyang","family":"Zhu","sequence":"first","affiliation":[{"name":"Department of Control Science and Intelligence Engineering, School of Management and Engineering, Nanjing University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiao","family":"Yin","sequence":"additional","affiliation":[{"name":"Department of Control Science and Intelligence Engineering, School of Management and Engineering, Nanjing University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3929-4707","authenticated-orcid":false,"given":"Chunlin","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Control Science and Intelligence Engineering, School of Management and Engineering, Nanjing University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"crossref","first-page":"484","DOI":"10.1038\/nature16961","article-title":"Mastering the game of go with deep neural networks and tree search","volume":"529","author":"silver","year":"2016","journal-title":"Nature"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939785"},{"key":"ref12","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref56","article-title":"Distilling the knowledge in a neural network","author":"hinton","year":"2015","journal-title":"ArXiv 1503 02531"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2021.3053414"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2010.2091408"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3055499"},{"key":"ref58","first-page":"1","article-title":"SUMO—Simulation of urban mobility: An overview","author":"behrisch","year":"2011","journal-title":"Proc 3rd Int Conf Adv Syst Simulation"},{"key":"ref53","first-page":"414","article-title":"Toward interpretable deep reinforcement learning with linear model U-trees","author":"liu","year":"2018","journal-title":"Proc Eur Conf Mach Learn Knowl Discovery Databases"},{"key":"ref52","article-title":"Distilling a neural network into a soft decision tree","author":"frosst","year":"2017","journal-title":"arXiv 1711 09784"},{"key":"ref11","first-page":"97","article-title":"Chaos-particle swarm optimization algorithm and its application to urban traffic control","volume":"6","author":"dong","year":"2006","journal-title":"Int J Comput Sci Netw Secur"},{"key":"ref55","article-title":"OpenAI gym","author":"brockman","year":"2016","journal-title":"arXiv 1606 01540 [cs]"},{"key":"ref10","first-page":"105","article-title":"A survey of intelligence methods in urban traffic signal control","volume":"7","author":"liu","year":"2007","journal-title":"Int J Comput Sci Netw Secur"},{"key":"ref54","first-page":"19622","article-title":"Learning tree interpretation from object representation for deep reinforcement learning","volume":"34","author":"liu","year":"2021","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2020.2997896"},{"key":"ref16","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","year":"2016","journal-title":"IEEE\/CAA Journal of Automatica Sinica"},{"key":"ref19","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"lecun","year":"2015","journal-title":"Nature"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2019.2901791"},{"key":"ref51","article-title":"CDT: Cascading decision trees for explainable reinforcement learning","author":"ding","year":"2020","journal-title":"arXiv 2011 07553"},{"key":"ref50","first-page":"12222","article-title":"Edge: Explaining deep reinforcement learning policies","volume":"34","author":"guo","year":"2021","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref46","article-title":"Deep reinforcement learning for traffic light control in vehicular networks","author":"liang","year":"2018","journal-title":"arXiv 1803 11115"},{"key":"ref45","article-title":"Using a deep reinforcement learning agent for traffic signal control","author":"genders","year":"2016","journal-title":"arXiv 1611 01142"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"ref47","first-page":"1995","article-title":"Dueling network architectures for deep reinforcement learning","author":"wang","year":"2016","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2019.8917268"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1061\/(ASCE)0733-947X(2003)129:3(278)"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TMECH.2021.3072675"},{"key":"ref43","article-title":"Adaptive traffic signal control: Deep reinforcement learning algorithm with experience replay and target network","author":"gao","year":"2017","journal-title":"arXiv 1705 02755"},{"key":"ref49","first-page":"1855","article-title":"Optimization methods for interpretable differentiable decision trees applied to reinforcement learning","author":"silva","year":"2020","journal-title":"Proc Int Conf Artif Intell Statist"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-45631-7_10"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.1977.4309605"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/S0952-1976(97)00010-9"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN48605.2020.9206820"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v25i1.7984"},{"key":"ref6","first-page":"130","article-title":"An overview and performance evaluation of ACS lite—A low cost adaptive signal control system","volume":"190","author":"shelby","year":"2008","journal-title":"Proc Transp Res Board Annu Meeting"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1287\/trsc.31.1.5"},{"key":"ref40","volume":"180","author":"bramer","year":"2007","journal-title":"Principles of Data Mining"},{"key":"ref35","article-title":"Fast interpretable greedy-tree sums (FIGS)","author":"tan","year":"2022","journal-title":"arXiv 2201 11931"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1214\/aos\/1013203451"},{"key":"ref37","author":"bellman","year":"2013","journal-title":"Dynamic Programming"},{"key":"ref36","first-page":"1","article-title":"Verifiable reinforcement learning via policy extraction","author":"bastani","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TMECH.2019.2899365"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TCSS.2022.3152179"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1023\/A:1010933404324"},{"key":"ref32","author":"breiman","year":"1984","journal-title":"Classification Regression Trees"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2015.2498160"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSS.2019.2904633"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/BF00116251"},{"key":"ref38","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33014561"},{"key":"ref23","first-page":"3658","article-title":"Interpretable off-policy evaluation in reinforcement learning by highlighting influential transitions","author":"gottesman","year":"2020","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3067057"},{"key":"ref25","first-page":"18375","article-title":"What did you think would happen? Explaining agent behaviour through intended outcomes","volume":"33","author":"yau","year":"2020","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref20","first-page":"628","article-title":"Why did you do that?’ explainable intelligent robots","author":"sheh","year":"2017","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"ref22","first-page":"50","article-title":"Discovering interpretable representations for both deep generative and discriminative models","author":"adel","year":"2018","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TCSS.2021.3096824"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TCSS.2021.3120421"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2021.3134329"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TCSS.2022.3161996"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2017.09.020"}],"container-title":["IEEE Transactions on Computational Social Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570650\/10201450\/09970401.pdf?arnumber=9970401","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,21]],"date-time":"2023-08-21T18:01:37Z","timestamp":1692640897000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9970401\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8]]},"references-count":60,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tcss.2022.3225362","relation":{},"ISSN":["2329-924X","2373-7476"],"issn-type":[{"value":"2329-924X","type":"electronic"},{"value":"2373-7476","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,8]]}}}