{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,24]],"date-time":"2026-07-24T15:15:49Z","timestamp":1784906149632,"version":"3.55.0"},"reference-count":48,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"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":[[2025,4]]},"DOI":"10.1109\/tnnls.2024.3409182","type":"journal-article","created":{"date-parts":[[2024,6,18]],"date-time":"2024-06-18T17:55:05Z","timestamp":1718733305000},"page":"6970-6980","source":"Crossref","is-referenced-by-count":13,"title":["Inverse Value Iteration and <i>Q<\/i>-Learning: Algorithms, Stability, and Robustness"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3275-9551","authenticated-orcid":false,"given":"Bosen","family":"Lian","sequence":"first","affiliation":[{"name":"Electrical and Computer Engineering Department, Auburn University, Auburn, AL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3670-3854","authenticated-orcid":false,"given":"Wenqian","family":"Xue","sequence":"additional","affiliation":[{"name":"Electrical and Computer Engineering Department, University of Florida, Gainesville, FL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4074-1615","authenticated-orcid":false,"given":"Frank L.","family":"Lewis","sequence":"additional","affiliation":[{"name":"The University of Texas at Arlington Research Institute, Fort Worth, TX, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2951-442X","authenticated-orcid":false,"given":"Ali","family":"Davoudi","sequence":"additional","affiliation":[{"name":"The University of Texas at Arlington Research Institute, Fort Worth, TX, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"2","article-title":"Algorithms for inverse reinforcement learning","volume-title":"Proc. 17th Int. Conf. Mach. Learn.","volume":"1","author":"Ng"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1115\/1.3653115"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1080\/00207179.2012.691180"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.23919\/ECC.2018.8550090"},{"key":"ref5","first-page":"897","article-title":"Apprenticeship learning about multiple intentions","volume-title":"Proc. 28th Int. Conf. Mach. Learn.","author":"Babes"},{"key":"ref6","first-page":"1433","article-title":"Maximum entropy inverse reinforcement learning","volume-title":"Proc. 23rd AAAI Conf. Artif. Intell.","volume":"8","author":"Ziebart"},{"key":"ref7","first-page":"19","article-title":"Nonlinear inverse reinforcement learning with Gaussian processes","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"24","author":"Levine"},{"key":"ref8","article-title":"Maximum entropy deep inverse reinforcement learning","author":"Wulfmeier","year":"2015","journal-title":"arXiv:1507.04888"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3051012"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TPWRS.2021.3076296"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2023.3305983"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TCBB.2018.2830357"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3114612"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2021.3062856"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2021.3100749"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.23919\/ACC.2018.8431430"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/LCSYS.2020.3046527"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2022.110242"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2023.111171"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.sysconle.2023.105658"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/tcyb.2023.3338197"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/SSCI51031.2022.10022226"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2023.3259581"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2023.3283542"},{"key":"ref25","article-title":"Learning timeinvariant reward functions through model-based inverse reinforcement learning","author":"Davchev","year":"2021","journal-title":"arXiv:2107.03186"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.arcontrol.2020.06.001"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2021.103500"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2017.8264504"},{"key":"ref29","article-title":"Deep inverse Q-learning with constraints","author":"Kalweit","year":"2020","journal-title":"arXiv:2008.01712"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2019.2921835"},{"issue":"5","key":"ref31","doi-asserted-by":"crossref","first-page":"2922","DOI":"10.1109\/TAC.2023.3235967","article-title":"Efficient off-policy Qlearning for data-based discrete-time LQR problems","volume":"68","author":"Lopez","year":"2023","journal-title":"IEEE Trans. Autom. Control"},{"key":"ref32","doi-asserted-by":"crossref","DOI":"10.1016\/j.automatica.2021.109548","article-title":"Low-complexity learning of linear quadratic regulators from noisy data","volume":"128","author":"De Persis","year":"2021","journal-title":"Automatica"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/s10208-019-09426-y"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2870075"},{"issue":"10","key":"ref35","doi-asserted-by":"crossref","first-page":"2699","DOI":"10.1016\/j.automatica.2012.06.096","article-title":"Computational adaptive optimal control for continuous-time linear systems with completely unknown dynamics","volume":"48","author":"Jiang","year":"2012","journal-title":"Automatica"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2022.3172590"},{"key":"ref37","first-page":"115","article-title":"Lyapunov stability","volume":"12","author":"Khalil","year":"2009","journal-title":"Control Syst., Robot. Autom."},{"key":"ref38","volume-title":"The Riccati Equation","author":"Bittanti","year":"2012"},{"key":"ref39","volume-title":"Functional Analysis","author":"Kantorovich","year":"1964"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.1968.1098829"},{"issue":"30","key":"ref41","first-page":"487","article-title":"Solutions of ill-posed problems","volume":"1","author":"Tikhonov","year":"1977","journal-title":"New York"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.1981.1102565"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2021.3082157"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.1994.735224"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2020.2987313"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2018.2889377"},{"issue":"1","key":"ref47","doi-asserted-by":"crossref","first-page":"11","DOI":"10.1049\/ip-c.1993.0003","article-title":"Robust load-frequency controller design for power systems","volume":"140","author":"Wang","year":"1993","journal-title":"IEE Proc. C, Gener., Transmiss. Distrib."},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2013.10.005"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/5962385\/10949581\/10560031.pdf?arnumber=10560031","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,5]],"date-time":"2025-04-05T06:17:18Z","timestamp":1743833838000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10560031\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4]]},"references-count":48,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2024.3409182","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4]]}}}