{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,22]],"date-time":"2026-03-22T05:45:36Z","timestamp":1774158336404,"version":"3.50.1"},"reference-count":21,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2021,4,1]],"date-time":"2021-04-01T00:00:00Z","timestamp":1617235200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,4,1]],"date-time":"2021-04-01T00:00:00Z","timestamp":1617235200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,4,1]],"date-time":"2021-04-01T00:00:00Z","timestamp":1617235200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2021,4]]},"DOI":"10.1109\/lra.2021.3061374","type":"journal-article","created":{"date-parts":[[2021,2,23]],"date-time":"2021-02-23T20:48:36Z","timestamp":1614113316000},"page":"2225-2232","source":"Crossref","is-referenced-by-count":104,"title":["Learning Variable Impedance Control via Inverse Reinforcement Learning for Force-Related Tasks"],"prefix":"10.1109","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7900-5127","authenticated-orcid":false,"given":"Xiang","family":"Zhang","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1248-2137","authenticated-orcid":false,"given":"Liting","family":"Sun","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2072-9638","authenticated-orcid":false,"given":"Zhian","family":"Kuang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0206-6639","authenticated-orcid":false,"given":"Masayoshi","family":"Tomizuka","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202244"},{"key":"ref11","first-page":"1334","article-title":"End-to-end training of deep visuomotor policies","volume":"17","author":"levine","year":"2016","journal-title":"J Mach Learn Res"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1115\/1.3139652"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1115\/1.3140713"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2018.2830405"},{"key":"ref15","article-title":"Continuous inverse optimal control with locally optimal examples","author":"levine","year":"0","journal-title":"Proc 29th Int Conf Mach Learn"},{"key":"ref16","article-title":"A connection between generative adversarial networks, inverse reinforcement learning, and energy-based models","volume":"abs 1611 3852","author":"finn","year":"2016","journal-title":"CoRR"},{"key":"ref17","article-title":"Learning robust rewards with adversarial inverse reinforcement learning","volume":"abs 1710 11248","author":"fu","year":"2017","journal-title":"CoRR"},{"key":"ref18","first-page":"1889","article-title":"Trust region policy optimization","author":"schulman","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1177\/0278364911402527"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/AIM.2016.7576815"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8968201"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-017-9636-y"},{"key":"ref8","first-page":"1433","article-title":"Maximum entropy inverse reinforcement learning","author":"ziebart","year":"0","journal-title":"Proc 23rd AAAI Conf Artif Intell"},{"key":"ref7","first-page":"49","article-title":"Guided cost learning: Deep inverse optimal control via policy optimization","author":"finn","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/HUMANOIDS.2018.8624938"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7139387"},{"key":"ref9","first-page":"305","article-title":"Alvinn: An autonomous land vehicle in a neural network","author":"pomerleau","year":"0","journal-title":"Proc Adv Neural Inform Process Syst"},{"key":"ref20","doi-asserted-by":"crossref","DOI":"10.23919\/ACC50511.2021.9482949","article-title":"Feedback-based digital higher-order terminal sliding mode for 6-dof industrial manipulators","author":"kuang","year":"2021"},{"key":"ref21","first-page":"358","article-title":"Precise linear-motor synchronization control via cross-coupled second-order discrete-time fractional-order sliding mode","volume":"26","author":"kuang","year":"2021","journal-title":"IEEE Trans Mechatron"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7083369\/9285111\/09361101.pdf?arnumber=9361101","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,18]],"date-time":"2022-12-18T18:58:27Z","timestamp":1671389907000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9361101\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,4]]},"references-count":21,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/lra.2021.3061374","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,4]]}}}