{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T02:28:26Z","timestamp":1730341706433,"version":"3.28.0"},"reference-count":27,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,5,31]],"date-time":"2023-05-31T00:00:00Z","timestamp":1685491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,5,31]],"date-time":"2023-05-31T00:00:00Z","timestamp":1685491200000},"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":[[2023,5,31]]},"DOI":"10.23919\/acc55779.2023.10156188","type":"proceedings-article","created":{"date-parts":[[2023,7,3]],"date-time":"2023-07-03T17:48:03Z","timestamp":1688406483000},"page":"3989-3994","source":"Crossref","is-referenced-by-count":0,"title":["Nonuniqueness and Convergence to Equivalent Solutions in Observer-based Inverse Reinforcement Learning"],"prefix":"10.23919","author":[{"given":"Jared","family":"Town","sequence":"first","affiliation":[{"name":"Oklahoma State University,School of Mechanical and Aerospace Engineering,Stillwater,OK,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zachary","family":"Morrison","sequence":"additional","affiliation":[{"name":"Oklahoma State University,School of Mechanical and Aerospace Engineering,Stillwater,OK,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rushikesh","family":"Kamalapurkar","sequence":"additional","affiliation":[{"name":"Oklahoma State University,School of Mechanical and Aerospace Engineering,Stillwater,OK,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3186229"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-009-9170-7"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/LCSYS.2020.3046527"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2022.110242"},{"key":"ref11","first-page":"19","article-title":"Nonlinear inverse reinforcement learning with Gaussian processes","author":"levine","year":"2011","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref10","first-page":"1449","article-title":"A game-theoretic approach to apprenticeship learning","author":"syed","year":"2008","journal-title":"Adv Neural Inf Process Syst"},{"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":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2873794"},{"key":"ref16","article-title":"On model-based online inverse reinforcement learning","author":"self","year":"2020","journal-title":"Ph D dissertation Oklahoma State University"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7139642"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1002\/rnc.5626"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3114612"},{"key":"ref23","article-title":"Inverse reinforcement learning in tracking control based on inverse optimal control","author":"xue","year":"2021","journal-title":"IEEE Trans Cybern"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1111\/j.2517-6161.1996.tb02080.x"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.2307\/1267352"},{"key":"ref20","first-page":"1170","article-title":"Online inverse reinforcement learning under occlusion","author":"arora","year":"2019","journal-title":"Proc Int Joint Conf Auton Agents Multiagent Syst"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2018.8619204"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1137\/0311001"},{"journal-title":"Nonlinear Systems","year":"2002","author":"khalil","key":"ref27"},{"key":"ref8","first-page":"1342","article-title":"Feature construction for inverse reinforcement learning","volume":"23","author":"levine","year":"2010","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2017.2775960"},{"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":"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 Intel"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143936"}],"event":{"name":"2023 American Control Conference (ACC)","start":{"date-parts":[[2023,5,31]]},"location":"San Diego, CA, USA","end":{"date-parts":[[2023,6,2]]}},"container-title":["2023 American Control Conference (ACC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10155646\/10155787\/10156188.pdf?arnumber=10156188","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,3]],"date-time":"2023-07-03T21:10:26Z","timestamp":1688418626000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10156188\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5,31]]},"references-count":27,"URL":"https:\/\/doi.org\/10.23919\/acc55779.2023.10156188","relation":{},"subject":[],"published":{"date-parts":[[2023,5,31]]}}}