{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T15:40:13Z","timestamp":1781797213335,"version":"3.54.5"},"reference-count":40,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2021,7,1]],"date-time":"2021-07-01T00:00:00Z","timestamp":1625097600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,7,1]],"date-time":"2021-07-01T00:00:00Z","timestamp":1625097600000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,7,1]],"date-time":"2021-07-01T00:00:00Z","timestamp":1625097600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,7,1]],"date-time":"2021-07-01T00:00:00Z","timestamp":1625097600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100008982","name":"National Science Foundation","doi-asserted-by":"publisher","award":["1849952"],"award-info":[{"award-number":["1849952"]}],"id":[{"id":"10.13039\/501100008982","id-type":"DOI","asserted-by":"publisher"}]},{"name":"FLI","award":["RFP2-000"],"award-info":[{"award-number":["RFP2-000"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2021,7]]},"DOI":"10.1109\/lra.2021.3068912","type":"journal-article","created":{"date-parts":[[2021,3,25]],"date-time":"2021-03-25T19:58:14Z","timestamp":1616702294000},"page":"5231-5238","source":"Crossref","is-referenced-by-count":14,"title":["Learning From Imperfect Demonstrations From Agents With Varying Dynamics"],"prefix":"10.1109","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5098-2194","authenticated-orcid":false,"given":"Zhangjie","family":"Cao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7802-9183","authenticated-orcid":false,"given":"Dorsa","family":"Sadigh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","author":"gmbh","year":"0","journal-title":"Introduction"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref33","article-title":"Continuous online learning and new insights to online imitation learning","author":"lee","year":"2019"},{"key":"ref32","first-page":"43","article-title":"When humans aren’t optimal: Robots that collaborate with risk-aware humans","author":"kwon","year":"0","journal-title":"Proc ACM\/IEEE Int Conf Hum -Robot Interact"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/s12369-012-0160-0"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/2909824.3020250"},{"key":"ref37","article-title":"Openai gym","author":"brockman","year":"2016"},{"key":"ref36","first-page":"1889","article-title":"Trust region policy optimization","author":"schulman","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00851"},{"key":"ref34","article-title":"Adversarial imitation via variational inverse reinforcement learning","author":"qureshi","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref10","first-page":"9407","article-title":"Variational imitation learning with diverse-quality demonstrations","author":"tangkaratt","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref40","article-title":"Pybullet physics engine","author":"coumans","year":"2018"},{"key":"ref11","first-page":"627","article-title":"A reduction of imitation learning and structured prediction to no-regret online learning","author":"ross","year":"0","journal-title":"Proc 14th Int Conf Artif Int Statist JMLR Workshop Conf Proc"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-009-5106-x"},{"key":"ref13","first-page":"661","article-title":"Efficient reductions for imitation learning","author":"ross","year":"0","journal-title":"Proc 13th Int Conf Artif Int Statist JMLR Workshop Conf Proc"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/1015330.1015430"},{"key":"ref15","first-page":"663","article-title":"Algorithms for inverse reinforcement learning","author":"ng","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref16","article-title":"Learning robust rewards with adverserial inverse reinforcement learning","author":"fu","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref17","article-title":"Wasserstein adversarial imitation learning","author":"xiao","year":"2019"},{"key":"ref18","first-page":"313","article-title":"Imitation learning as $ f$-divergence minimization","author":"ke","year":"0","journal-title":"Workshop Algorithmic Found Robot"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/687"},{"key":"ref28","article-title":"State alignment-based imitation learning","author":"liu","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2020.XVI.039"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2009.5152466"},{"key":"ref3","article-title":"Generative adversarial imitation learning","volume":"29","author":"ho","year":"0","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197197"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460487"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/4711.001.0001"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2011.5979757"},{"key":"ref7","first-page":"6818","article-title":"Imitation learning from imperfect demonstration","author":"wu","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref2","first-page":"1433","article-title":"Maximum entropy inverse reinforcement learning","volume":"8","author":"ziebart","year":"0","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"ref9","article-title":"Learning sparse rewarded tasks from sub-optimal demonstrations","author":"zhu","year":"2020"},{"key":"ref1","first-page":"103","article-title":"A framework for behavioural cloning","volume":"15","author":"bain","year":"1995","journal-title":"Mach Intell"},{"key":"ref20","first-page":"2915","article-title":"State aware imitation learning","author":"schroecker","year":"0","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref22","first-page":"6036","article-title":"Provably efficient imitation learning from observation alone","author":"sun","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref21","article-title":"Generative adversarial imitation from observation","author":"torabi","year":"2019","journal-title":"Imitation Intent and Interaction (I3) Workshop at ICML"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2008.10.024"},{"key":"ref23","doi-asserted-by":"crossref","DOI":"10.7551\/mitpress\/3676.003.0003","article-title":"The correspondence problem","volume":"41","author":"nehaniv","year":"2002","journal-title":"Imitation in Animals and Artifacts"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2006.886952"},{"key":"ref25","article-title":"Addressing the correspondence problem by model-based imitation learning","author":"englert","year":"0","journal-title":"ICRA Workshop on Autonomous Learning"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/7083369\/9399748\/9387082-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7083369\/9399748\/09387082.pdf?arnumber=9387082","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,26]],"date-time":"2024-08-26T21:04:36Z","timestamp":1724706276000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9387082\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7]]},"references-count":40,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/lra.2021.3068912","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,7]]}}}