{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T22:45:37Z","timestamp":1775601937430,"version":"3.50.1"},"reference-count":39,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2023,5,1]],"date-time":"2023-05-01T00:00:00Z","timestamp":1682899200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,5,1]],"date-time":"2023-05-01T00:00:00Z","timestamp":1682899200000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,5,1]],"date-time":"2023-05-01T00:00:00Z","timestamp":1682899200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,5,1]],"date-time":"2023-05-01T00:00:00Z","timestamp":1682899200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"publisher","award":["61991400"],"award-info":[{"award-number":["61991400"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"publisher","award":["61991404"],"award-info":[{"award-number":["61991404"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"publisher","award":["61991403"],"award-info":[{"award-number":["61991403"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"publisher","award":["61533015"],"award-info":[{"award-number":["61533015"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100013314","name":"111 Project","doi-asserted-by":"publisher","award":["B08015"],"award-info":[{"award-number":["B08015"]}],"id":[{"id":"10.13039\/501100013314","id-type":"DOI","asserted-by":"publisher"}]},{"name":"2020 Science and Technology Major Project of Liaoning Province","award":["2020JH1\/10100008"],"award-info":[{"award-number":["2020JH1\/10100008"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2023,5]]},"DOI":"10.1109\/tnnls.2021.3106635","type":"journal-article","created":{"date-parts":[[2021,9,14]],"date-time":"2021-09-14T20:11:35Z","timestamp":1631650295000},"page":"2386-2399","source":"Crossref","is-referenced-by-count":64,"title":["Inverse Reinforcement Q-Learning Through Expert Imitation for Discrete-Time Systems"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3670-3854","authenticated-orcid":false,"given":"Wenqian","family":"Xue","sequence":"first","affiliation":[{"name":"State Key Laboratory of Synthetical Automation for Process Industries, Northeastern University, Shenyang, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3275-9551","authenticated-orcid":false,"given":"Bosen","family":"Lian","sequence":"additional","affiliation":[{"name":"UTA Research Institute, University of Texas at Arlington, Arlington, TX, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7585-1166","authenticated-orcid":false,"given":"Jialu","family":"Fan","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Synthetical Automation for Process Industries, Northeastern University, Shenyang, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4332-3462","authenticated-orcid":false,"given":"Patrik","family":"Kolaric","sequence":"additional","affiliation":[{"name":"UTA Research Institute, University of Texas at Arlington, Arlington, TX, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4623-1483","authenticated-orcid":false,"given":"Tianyou","family":"Chai","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Synthetical Automation for Process Industries, Northeastern University, Shenyang, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4074-1615","authenticated-orcid":false,"given":"Frank L.","family":"Lewis","sequence":"additional","affiliation":[{"name":"UTA Research Institute, University of Texas at Arlington, Arlington, TX, USA"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.3390\/app9091807"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2012.06.096"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2019.12.023"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1002\/rnc.5626"},{"key":"ref15","first-page":"12","article-title":"Robot learning from demonstration","volume":"97","author":"atkeson","year":"1997","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2006.09.019"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/S1364-6613(99)01327-3"},{"key":"ref36","article-title":"Off-policy reinforcement learning for tracking in continuous-time systems on two time scales","author":"xue","year":"2020","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CCA.2011.6044461"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2014.2350511"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3011194"},{"key":"ref33","article-title":"Inverse reinforcement learning in tracking control based on inverse optimal control","author":"xue","year":"2021","journal-title":"IEEE Trans Cybern"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2018.2890046"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1201\/b14779"},{"key":"ref2","author":"barto","year":"1998","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1002\/9781118122631"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1177\/0278364910371999"},{"key":"ref39","doi-asserted-by":"crossref","DOI":"10.1093\/oso\/9780198537953.001.0001","author":"lancaster","year":"1995","journal-title":"Algebraic Riccati Equations"},{"key":"ref16","first-page":"4565","article-title":"Generative adversarial imitation learning","author":"ho","year":"2016","journal-title":"Proc Conf Neural Inf Process Syst"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1108\/aeat.2004.12776eae.001"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/1015330.1015430"},{"key":"ref18","first-page":"1","article-title":"Apprenticeship learning about multiple intentions","author":"babes","year":"2011","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref24","article-title":"Deep inverse Q-learning with constraints","author":"kalweit","year":"2020","journal-title":"arXiv 2008 01712"},{"key":"ref23","first-page":"49","article-title":"Guided cost learning: Deep inverse optimal control via policy optimization","author":"finn","year":"2016","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1115\/1.3653115"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.2307\/j.ctvcm4hws"},{"key":"ref20","article-title":"Apprenticeship learning using inverse reinforcement learning and gradient methods","author":"neu","year":"2012","journal-title":"arXiv 1206 5264"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/s12555-015-0483-3"},{"key":"ref21","first-page":"3909","article-title":"Cooperative inverse reinforcement learning","author":"hadfield-menell","year":"2016","journal-title":"Proc 30th Conf Neural Inf Process Syst"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.ast.2012.11.006"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2013.6760325"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2005.858694"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2017.2771459"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2014.02.015"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2016.12.009"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2014.2317301"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/MCAS.2009.933854"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2014.05.011"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2015.2441749"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/5962385\/10114428\/9537731-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/10114428\/09537731.pdf?arnumber=9537731","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,8]],"date-time":"2023-11-08T20:10:07Z","timestamp":1699474207000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9537731\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5]]},"references-count":39,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2021.3106635","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,5]]}}}