{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T06:06:02Z","timestamp":1780725962507,"version":"3.54.1"},"reference-count":30,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2021,12,1]],"date-time":"2021-12-01T00:00:00Z","timestamp":1638316800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,12,1]],"date-time":"2021-12-01T00:00:00Z","timestamp":1638316800000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,12,1]],"date-time":"2021-12-01T00:00:00Z","timestamp":1638316800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,12,1]],"date-time":"2021-12-01T00:00:00Z","timestamp":1638316800000},"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","award":["1925147"],"award-info":[{"award-number":["1925147"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Control Syst. Lett."],"published-print":{"date-parts":[[2021,12]]},"DOI":"10.1109\/lcsys.2020.3046527","type":"journal-article","created":{"date-parts":[[2020,12,22]],"date-time":"2020-12-22T21:01:07Z","timestamp":1608670867000},"page":"1922-1927","source":"Crossref","is-referenced-by-count":29,"title":["Online Observer-Based Inverse Reinforcement Learning"],"prefix":"10.1109","volume":"5","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8752-6299","authenticated-orcid":false,"given":"Ryan","family":"Self","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kevin","family":"Coleman","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4247-0698","authenticated-orcid":false,"given":"He","family":"Bai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9963-5361","authenticated-orcid":false,"given":"Rushikesh","family":"Kamalapurkar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref30","author":"self","year":"2020","journal-title":"Online observer-based inverse reinforcement learning"},{"key":"ref10","first-page":"1342","article-title":"Feature construction for inverse reinforcement learning","author":"levine","year":"2010","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref11","first-page":"19","article-title":"Nonlinear inverse reinforcement learning with Gaussian processes","author":"levine","year":"2011","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref12","first-page":"1413","article-title":"Inverse reinforcement learning in swarm systems","author":"\u0161o\u0161i?","year":"2017","journal-title":"Proc Int Joint Conf Auton Agents Multiagent Syst"},{"key":"ref13","first-page":"5143","article-title":"Competitive multi-agent inverse reinforcement learning with sub-optimal demonstrations","volume":"80","author":"wang","year":"2018","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33486-3_10"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2010.02.018"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2015.2466191"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-78384-0"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2018.8619314"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.23919\/ACC.2018.8431430"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.23919\/ACC.2017.7963838"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1115\/1.3653115"},{"key":"ref27","author":"horn","year":"1993","journal-title":"Matrix Analysis"},{"key":"ref3","first-page":"554","article-title":"Inverse reinforcement learning","author":"abbeel","year":"2010","journal-title":"Encyclopedia of Machine Learning"},{"key":"ref6","first-page":"1433","article-title":"Maximum entropy inverse reinforcement learning","author":"ziebart","year":"2008","journal-title":"Proc AAAI Conf Artif Intel"},{"key":"ref29","author":"self","year":"0","journal-title":"Online simultaneous state and parameter estimation"},{"key":"ref5","first-page":"1040","article-title":"Learning from demonstration","author":"schaal","year":"1997","journal-title":"Advances in Neural Information Processing Systems 9"},{"key":"ref8","author":"wulfmeier","year":"2015","journal-title":"Maximum entropy deep inverse reinforcement learning"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143936"},{"key":"ref2","first-page":"663","article-title":"Algorithms for inverse reinforcement learning","author":"ng","year":"2000","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016722"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/279943.279964"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CCTA.2019.8920458"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.23919\/ACC45564.2020.9147344"},{"key":"ref21","article-title":"Online inverse reinforcement learning with limited data","author":"self","year":"2020","journal-title":"Proc IEEE Conf Decis Control"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1515\/9781400842643"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CDC40024.2019.9029636"},{"key":"ref26","author":"khalil","year":"2002","journal-title":"Nonlinear Systems"},{"key":"ref25","author":"sastry","year":"1989","journal-title":"Adaptive Control Stability Convergence and Robustness"}],"container-title":["IEEE Control Systems Letters"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/7782633\/9366631\/9302679-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7782633\/9366631\/09302679.pdf?arnumber=9302679","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:54:20Z","timestamp":1652194460000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9302679\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12]]},"references-count":30,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/lcsys.2020.3046527","relation":{},"ISSN":["2475-1456"],"issn-type":[{"value":"2475-1456","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,12]]}}}