{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,21]],"date-time":"2026-02-21T20:30:26Z","timestamp":1771705826528,"version":"3.50.1"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,12,14]],"date-time":"2020-12-14T00:00:00Z","timestamp":1607904000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,12,14]],"date-time":"2020-12-14T00:00:00Z","timestamp":1607904000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,12,14]],"date-time":"2020-12-14T00:00:00Z","timestamp":1607904000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020,12,14]]},"DOI":"10.1109\/cdc42340.2020.9303883","type":"proceedings-article","created":{"date-parts":[[2021,1,13]],"date-time":"2021-01-13T07:27:32Z","timestamp":1610522852000},"page":"603-608","source":"Crossref","is-referenced-by-count":10,"title":["Online inverse reinforcement learning with limited data"],"prefix":"10.1109","author":[{"given":"Ryan","family":"Self","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"S M Nahid","family":"Mahmud","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Katrine","family":"Hareland","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rushikesh","family":"Kamalapurkar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","first-page":"1449","article-title":"A game-theoretic approach to apprenticeship learning","author":"syed","year":"2008","journal-title":"Advances in Neural Information Processing Systems 20"},{"key":"ref11","first-page":"19","article-title":"Nonlinear inverse reinforcement learning with Gaussian processes","author":"levine","year":"2011","journal-title":"Advances in Neural Information Processing Systems 24"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.23919\/ACC.2018.8431430"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2018.8619314"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CCTA.2019.8920458"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.23919\/ACC45564.2020.9147344"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/0893-6080(89)90020-8"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/0893-6080(91)90009-T"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1515\/9781400842643"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.23919\/ACC.2017.7963838"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/1102351.1102352"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/1015330.1015430"},{"key":"ref6","first-page":"1433","article-title":"Maximum entropy inverse reinforcement learning","author":"ziebart","year":"2008","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143936"},{"key":"ref8","first-page":"1342","article-title":"Feature construction for inverse reinforcement learning","author":"levine","year":"2010","journal-title":"Advances in Neural Information Processing Systems 23"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2017.2775960"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/279943.279964"},{"key":"ref1","first-page":"663","article-title":"Algorithms for inverse reinforcement learning","author":"ng","year":"2000","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref9","first-page":"295","article-title":"Apprenticeship learning using inverse reinforcement learning and gradient methods","author":"neu","year":"2007","journal-title":"Proc Conf Uncertainty of Artificial Intelligence"},{"key":"ref20","doi-asserted-by":"crossref","first-page":"94","DOI":"10.1016\/j.automatica.2015.10.039","article-title":"Modelbased reinforcement learning for approximate optimal regulation","volume":"64","author":"kamalapurkar","year":"2016","journal-title":"Automatica"},{"key":"ref22","doi-asserted-by":"crossref","DOI":"10.1109\/CDC42340.2020.9303883","article-title":"Online inverse reinforcement learning with limited data","author":"self","year":"2020"},{"key":"ref21","author":"ioannou","year":"1996","journal-title":"Robust Adaptive Control"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2015.2511658"},{"key":"ref23","doi-asserted-by":"crossref","first-page":"40","DOI":"10.1016\/j.automatica.2014.10.103","article-title":"Approximate optimal trajectory tracking for continuous-time nonlinear systems","volume":"51","author":"kamalapurkar","year":"2015","journal-title":"Automatica"}],"event":{"name":"2020 59th IEEE Conference on Decision and Control (CDC)","location":"Jeju, Korea (South)","start":{"date-parts":[[2020,12,14]]},"end":{"date-parts":[[2020,12,18]]}},"container-title":["2020 59th IEEE Conference on Decision and Control (CDC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9303728\/9303729\/09303883.pdf?arnumber=9303883","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,27]],"date-time":"2022-06-27T16:03:51Z","timestamp":1656345831000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9303883\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,12,14]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/cdc42340.2020.9303883","relation":{},"subject":[],"published":{"date-parts":[[2020,12,14]]}}}