{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T16:13:58Z","timestamp":1775578438578,"version":"3.50.1"},"reference-count":45,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","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\/100000006","name":"Office of Naval Research","doi-asserted-by":"publisher","award":["N00014-18-1-2221"],"award-info":[{"award-number":["N00014-18-1-2221"]}],"id":[{"id":"10.13039\/100000006","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000183","name":"Army Research Office","doi-asserted-by":"publisher","award":["W911NF-20-1-0132"],"award-info":[{"award-number":["W911NF-20-1-0132"]}],"id":[{"id":"10.13039\/100000183","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2023,8]]},"DOI":"10.1109\/tnnls.2021.3114612","type":"journal-article","created":{"date-parts":[[2021,10,10]],"date-time":"2021-10-10T22:30:46Z","timestamp":1633905046000},"page":"4596-4609","source":"Crossref","is-referenced-by-count":51,"title":["Inverse Reinforcement Learning for Adversarial Apprentice Games"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3275-9551","authenticated-orcid":false,"given":"Bosen","family":"Lian","sequence":"first","affiliation":[{"name":"University of Texas at Arlington Research Institute, Fort Worth, TX, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3670-3854","authenticated-orcid":false,"given":"Wenqian","family":"Xue","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Synthetical Automation for Process Industries and the International Joint Research Laboratory of Integrated Automation, Northeastern University, Shenyang, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4074-1615","authenticated-orcid":false,"given":"Frank L.","family":"Lewis","sequence":"additional","affiliation":[{"name":"University of Texas at Arlington Research Institute, Fort Worth, 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 and the International Joint Research Laboratory of Integrated Automation, Northeastern University, Shenyang, China"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2011.2173412"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2010.5716974"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2021.103500"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/j.arcontrol.2020.06.001"},{"key":"ref15","first-page":"322","article-title":"Friend-or-foe Q-learning in general-sum games","volume":"1","author":"littman","year":"2001","journal-title":"Proc 8th Int Conf Mach Learn"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1177\/0278364910371999"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1002\/9781118122631"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/s12555-015-0483-3"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1201\/b14779"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2013.6760325"},{"key":"ref11","first-page":"4565","article-title":"Generative adversarial imitation learning","author":"ho","year":"2016","journal-title":"Proc Conf Neural Inf Process Syst"},{"key":"ref33","article-title":"Continuous inverse optimal control with locally optimal examples","author":"levine","year":"2012","journal-title":"arXiv 1206 4617"},{"key":"ref10","first-page":"12","article-title":"Robot learning from demonstration","volume":"97","author":"atkeson","year":"1997","journal-title":"Proc 14th Int Conf Mach Learn"},{"key":"ref32","first-page":"767","article-title":"Trajectory tracking on complex networks via inverse optimal pinning control","volume":"64","author":"vega","year":"2019","journal-title":"IEEE Trans Autom Control"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/1015330.1015430"},{"key":"ref1","first-page":"663","article-title":"Algorithms for inverse reinforcement learning","volume":"1","author":"ng","year":"2000","journal-title":"Proc 17th Int Conf Mach Learn"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.2970969"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2018.8619204"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2015.2441749"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/s10846-009-9331-0"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TCNS.2019.2927201"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511811654"},{"key":"ref24","article-title":"Inverse reinforcement Q-learning through expert imitation for discrete-time systems","author":"xue","year":"2021","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11755"},{"key":"ref45","article-title":"Constrained nonlinear optimal control: A converse HJB approach","author":"nevisti?","year":"1996"},{"key":"ref26","article-title":"Inverse reinforcement learning in tracking control based on inverse optimal control","author":"xue","year":"2021","journal-title":"IEEE Trans Cybern"},{"key":"ref25","article-title":"Robust inverse Q-learning for continuous-time linear systems in adversarial environments","author":"lian","year":"2021","journal-title":"IEEE Trans Cybern"},{"key":"ref20","first-page":"19","article-title":"Nonlinear inverse reinforcement learning with Gaussian processes","volume":"24","author":"levine","year":"2011","journal-title":"Proc 25th Annu Conf Neural Inf Process Syst (NeurIPS)"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2008.2000204"},{"key":"ref41","article-title":"Beyond regression’: New tools for prediction and analysis in the behavioral sciences","author":"werbos","year":"1974"},{"key":"ref22","article-title":"Scalable inverse reinforcement learning through multifidelity Bayesian optimization","author":"imani","year":"2021","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"ref44","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":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TCBB.2018.2830357"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2014.2319577"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1115\/1.3653115"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1002\/rnc.5626"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.2307\/j.ctvcm4hws"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.23919\/ACC45564.2020.9147344"},{"key":"ref7","article-title":"Disturbance-aware neuro-optimal system control using generative adversarial control networks","author":"chu","year":"2020","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-247-2.50055-3"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCIAIG.2017.2679115"},{"key":"ref3","first-page":"1449","article-title":"A game-theoretic approach to apprenticeship learning","author":"syed","year":"2008","journal-title":"Proc 22nd Annu Conf Neural Inf Process Syst (NeurIPS)"},{"key":"ref6","article-title":"Multi-agent generative adversarial imitation learning","author":"song","year":"2018","journal-title":"arXiv 1807 09936"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.11541"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2011.6160778"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/10208115\/09565156.pdf?arnumber=9565156","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,21]],"date-time":"2023-08-21T17:57:28Z","timestamp":1692640648000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9565156\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8]]},"references-count":45,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2021.3114612","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,8]]}}}