{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,24]],"date-time":"2026-04-24T13:52:28Z","timestamp":1777038748260,"version":"3.51.4"},"reference-count":40,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2022,4,1]],"date-time":"2022-04-01T00:00:00Z","timestamp":1648771200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,4,1]],"date-time":"2022-04-01T00:00:00Z","timestamp":1648771200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,4,1]],"date-time":"2022-04-01T00:00:00Z","timestamp":1648771200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"BrainLinks-BrainTools Center"},{"DOI":"10.13039\/501100002714","name":"Albert-Ludwigs-Universit\u00e4t Freiburg","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002714","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2022,4]]},"DOI":"10.1109\/lra.2022.3145516","type":"journal-article","created":{"date-parts":[[2022,1,25]],"date-time":"2022-01-25T20:30:11Z","timestamp":1643142611000},"page":"3695-3702","source":"Crossref","is-referenced-by-count":37,"title":["Correct Me If I am Wrong: Interactive Learning for Robotic Manipulation"],"prefix":"10.1109","volume":"7","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7928-9377","authenticated-orcid":false,"given":"Eugenio","family":"Chisari","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1163-4992","authenticated-orcid":false,"given":"Tim","family":"Welschehold","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Joschka","family":"Boedecker","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5680-6500","authenticated-orcid":false,"given":"Wolfram","family":"Burgard","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4710-3114","authenticated-orcid":false,"given":"Abhinav","family":"Valada","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2019.XV.011"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.aau5872"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2020.2988642"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9562079"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3092685"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-28619-4_3"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-021-05961-4"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1561\/9781680834116"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1177\/0278364910371999"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2014.X.011"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1177\/0278364910392608"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.3389\/frobt.2021.650325"},{"key":"ref13","first-page":"627","article-title":"A reduction of imitation learning and structured prediction to no-regret online learning","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Ross","year":"2011"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/S0921-8890(02)00168-9"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/566570.566597"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/DEVLRN.2008.4640845"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/1597735.1597738"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11485"},{"key":"ref19","first-page":"2625","article-title":"Policy shaping: Integrating human feedback with reinforcement learning","volume":"26","author":"Griffith","year":"2013","journal-title":"Adv. Neural Info. Process. Syst."},{"key":"ref20","first-page":"3366","article-title":"Policy shaping with human teachers","volume-title":"Proc. Int. Conf. Artif. Intell.","author":"Cederborg","year":"2015"},{"key":"ref21","first-page":"2285","article-title":"Interactive learning from policy-dependent human feedback","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"MacGlashan","year":"2017"},{"key":"ref22","article-title":"Deep reinforcement learning from policy-dependent human feedback","volume-title":"CoRR","author":"Arumugam","year":"2019"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460854"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1613\/jair.2584"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICHR.2010.5686326"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793698"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICAR.2015.7251514"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793675"},{"key":"ref29","article-title":"Human-in-the-loop imitation learning using remote teleoperation","volume-title":"CoRR","author":"Mandlekar","year":"2020"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-23780-5_11"},{"key":"ref31","first-page":"1503","article-title":"Programming by feedback","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Schoenauer","year":"2014"},{"key":"ref32","first-page":"575","article-title":"Learning trajectory preferences for manipulators via iterative improvement","volume-title":"NIPS","author":"Jain","year":"2013"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1177\/0278364915581193"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2019.XV.023"},{"key":"ref35","first-page":"1177","article-title":"Asking easy questions: A user-friendly approach to active reward learning","volume-title":"CoRL","author":"Biyik"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2020.XVI.041"},{"key":"ref37","first-page":"4299","article-title":"Deep reinforcement learning from human preferences","volume-title":"NIPS","author":"Christiano"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2974707"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1707.06347"},{"key":"ref40","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Haarnoja","year":"2018"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7083369\/9647862\/09691826.pdf?arnumber=9691826","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,13]],"date-time":"2024-01-13T22:31:43Z","timestamp":1705185103000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9691826\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,4]]},"references-count":40,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/lra.2022.3145516","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,4]]}}}