{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,19]],"date-time":"2025-12-19T09:35:48Z","timestamp":1766136948294,"version":"3.37.3"},"reference-count":30,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2018,7,1]],"date-time":"2018-07-01T00:00:00Z","timestamp":1530403200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"name":"Marie Sklodowska-Curie Individual Fellowship LEACON","award":["659265"],"award-info":[{"award-number":["659265"]}]},{"name":"Technical University of Munich, International Graduate School of Science and Engineering and Helmholtz Association"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2018,7]]},"DOI":"10.1109\/lra.2018.2800110","type":"journal-article","created":{"date-parts":[[2018,1,31]],"date-time":"2018-01-31T19:19:30Z","timestamp":1517426370000},"page":"1482-1489","source":"Crossref","is-referenced-by-count":26,"title":["On Policy Learning Robust to Irreversible Events: An Application to Robotic In-Hand Manipulation"],"prefix":"10.1109","volume":"3","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1133-0884","authenticated-orcid":false,"given":"Pietro","family":"Falco","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8582-8178","authenticated-orcid":false,"given":"Abdallah","family":"Attawia","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Matteo","family":"Saveriano","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1897-7664","authenticated-orcid":false,"given":"Dongheui","family":"Lee","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8206343"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2013.6631137"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2017.2765668"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2014.6907059"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2013.6630637"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/HUMANOIDS.2015.7363524"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2016.7759557"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487156"},{"key":"ref17","article-title":"Learning complex dexterous manipulation with deep reinforcement learning and demonstrations","author":"rajeswaran","year":"2017","journal-title":"arXiv 1709 10087"},{"key":"ref18","article-title":"Learning dexterous manipulation policies\n from experience and imitation","author":"kumar","year":"2016","journal-title":"arXiv 1611 05095"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2016.7759394"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2009.5354022"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913514466"},{"key":"ref27","article-title":"The role of\n coupling terms in variable impedance policies learning","author":"winter","year":"0","journal-title":"International Workshop on Human-Friendly Robotic"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1177\/0278364915592961"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1080\/01691864.2014.946446"},{"key":"ref29","article-title":"Pi-rem: Policy improvement with residual\n model learning","author":"saveriano","year":"0","journal-title":"Proc 10th Int Workshop Human-Friendly Robot"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7139740"},{"key":"ref8","article-title":"Data-efficient deep reinforcement learning for\n dexterous manipulation","author":"popov","year":"2017","journal-title":"arXiv 1704 03073"},{"key":"ref7","first-page":"1","article-title":"End-to-end training of deep visuomotor\n policies","volume":"17","author":"levine","year":"2016","journal-title":"J Mach Learn Res"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913518997"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2017.2693391"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2013.6630954"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487124"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2014.01.005"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2017.2719761"},{"journal-title":"Modern Control Engineering","year":"1970","author":"ogata","key":"ref24"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.218"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487533"},{"journal-title":"Pattern Recognition and Machine Learning (Information Science and Statistics)","year":"2006","author":"bishop","key":"ref25"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7083369\/8302435\/08276248.pdf?arnumber=8276248","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T16:17:59Z","timestamp":1642004279000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/8276248\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,7]]},"references-count":30,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/lra.2018.2800110","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"type":"electronic","value":"2377-3766"},{"type":"electronic","value":"2377-3774"}],"subject":[],"published":{"date-parts":[[2018,7]]}}}