{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,13]],"date-time":"2026-03-13T07:51:46Z","timestamp":1773388306938,"version":"3.50.1"},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,5,30]],"date-time":"2021-05-30T00:00:00Z","timestamp":1622332800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,5,30]],"date-time":"2021-05-30T00:00:00Z","timestamp":1622332800000},"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":[],"published-print":{"date-parts":[[2021,5,30]]},"DOI":"10.1109\/icra48506.2021.9560829","type":"proceedings-article","created":{"date-parts":[[2021,10,20]],"date-time":"2021-10-20T00:28:35Z","timestamp":1634689715000},"page":"2877-2883","source":"Crossref","is-referenced-by-count":20,"title":["Learning Human Objectives from Sequences of Physical Corrections"],"prefix":"10.1109","author":[{"given":"Mengxi","family":"Li","sequence":"first","affiliation":[{"name":"Stanford University,Intelligent and Interactive Autonomous Systems Group (ILIAD),Dept of Computer Science,Stanford,CA,94305"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alper","family":"Canberk","sequence":"additional","affiliation":[{"name":"Stanford University,Intelligent and Interactive Autonomous Systems Group (ILIAD),Dept of Computer Science,Stanford,CA,94305"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dylan P.","family":"Losey","sequence":"additional","affiliation":[{"name":"Virginia Tech,Collaborative Robotics Lab (Collab)"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dorsa","family":"Sadigh","sequence":"additional","affiliation":[{"name":"Stanford University,Intelligent and Interactive Autonomous Systems Group (ILIAD),Dept of Computer Science,Stanford,CA,94305"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-32552-1_69"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.mechmachtheory.2007.03.003"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/MRA.2011.2181676"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1115\/1.3140713"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2008.4650764"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2015.2419873"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1115\/1.4039145"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/THMS.2018.2791570"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1177\/0278364912455366"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1177\/0278364918776060"},{"key":"ref28","first-page":"2586","article-title":"Bayesian inverse reinforcement learning","volume":"7","author":"ramachandran","year":"2007","journal-title":"IJCAI"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2020.2971415"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7139510"},{"key":"ref3","article-title":"Including uncertainty when learning from human corrections","author":"losey","year":"2018","journal-title":"Conference on Robot Learning"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2008.10.024"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s12369-012-0160-0"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143936"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1561\/2300000053"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3171221.3171267"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1177\/0278364915581193"},{"key":"ref1","first-page":"217","article-title":"Learning robot objectives from physical human interaction","author":"bajcsy","year":"2017","journal-title":"Conference on Robot Learning (CoRL)"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913490324"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2020.XVI.011"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3359614"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/1015330.1015430"},{"key":"ref23","first-page":"1433","article-title":"Maximum entropy inverse reinforcement learning","volume":"8","author":"ziebart","year":"2008","journal-title":"AAAI"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2017.2765335"},{"key":"ref25","article-title":"Reward-rational (implicit) choice: A unifying formalism for reward learning","author":"jeon","year":"2020"}],"event":{"name":"2021 IEEE International Conference on Robotics and Automation (ICRA)","location":"Xi'an, China","start":{"date-parts":[[2021,5,30]]},"end":{"date-parts":[[2021,6,5]]}},"container-title":["2021 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9560720\/9560666\/09560829.pdf?arnumber=9560829","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,2]],"date-time":"2022-08-02T23:21:52Z","timestamp":1659482512000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9560829\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,5,30]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/icra48506.2021.9560829","relation":{},"subject":[],"published":{"date-parts":[[2021,5,30]]}}}