{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,8]],"date-time":"2024-09-08T08:57:02Z","timestamp":1725785822818},"reference-count":27,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,11]]},"DOI":"10.1109\/humanoids.2018.8624972","type":"proceedings-article","created":{"date-parts":[[2019,1,25]],"date-time":"2019-01-25T02:51:38Z","timestamp":1548384698000},"page":"270-276","source":"Crossref","is-referenced-by-count":7,"title":["User Feedback in Latent Space Robotic Skill Learning"],"prefix":"10.1109","author":[{"given":"Rok","family":"Pahic","sequence":"first","affiliation":[]},{"given":"Zvezdan","family":"Loncarevic","sequence":"additional","affiliation":[]},{"given":"Ales","family":"Ude","sequence":"additional","affiliation":[]},{"given":"Bojan","family":"Nemec","sequence":"additional","affiliation":[]},{"given":"Andrej","family":"Gams","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","article-title":"Interactive q-learning with ordinal rewards and unreliable tutor","author":"weng","year":"2013","journal-title":"European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML\/PKDD)"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.2478\/pjbr-2013-0003"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1162\/NECO_a_00393"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2014.6942745"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2016.7759578"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/HUMANOIDS.2015.7363570"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/HUMANOIDS.2016.7803340"},{"key":"ref17","first-page":"663","article-title":"Algorithms for inverse reinforcement learning","author":"ng","year":"2000","journal-title":"Proc Seventh Int Conf Machine Learning"},{"key":"ref18","article-title":"Learning robust rewards with adversarial inverse reinforcement learning","author":"justin","year":"0","journal-title":"arXiv 1710 11248 2017"},{"journal-title":"Theory and Application of Reward Shaping in Reinforcement Learning","year":"2004","author":"laud","key":"ref19"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1080\/01691864.2013.814211"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2008.2006703"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICHR.2010.5686841"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913495721"},{"key":"ref5","article-title":"Solving the correspondence problem between dissimilarly embodied robotic arms using the alice imitation mechanism","author":"alissandrakis","year":"2003","journal-title":"Second International Symposium on Imitation in Animals and Artifacts"},{"key":"ref8","first-page":"388","article-title":"A survey on policy search for robotics","author":"deisenroth","year":"2013","journal-title":"Foundations and Trends in Robotics"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-010-5223-6"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/S1364-6613(99)01327-3"},{"key":"ref1","article-title":"Towards robot skill learning: From simple skills to table tennis","author":"peters","year":"2013","journal-title":"European Conference on Machine Learning (ECML)"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.3389\/frobt.2018.00077"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2015.09.011"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2017.XIII.053"},{"key":"ref21","article-title":"Deep reinforcement learning from human preferences","author":"christiano","year":"2017","journal-title":"arXiv preprint arXiv 1706 03741"},{"key":"ref24","first-page":"1","article-title":"Reinforcement learning combined with human feedback in continuous state and action spaces","author":"vien","year":"2012","journal-title":"IEEE Int Conf on Develop and Learn and Epigen Rob (ICDL)"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/1597735.1597738"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/Humanoids.2011.6100913"},{"key":"ref25","first-page":"1503","article-title":"Program-ming by Feedback","author":"akrour","year":"2014","journal-title":"International Conference on Machine Learning"}],"event":{"name":"2018 IEEE-RAS 18th International Conference on Humanoid Robots (Humanoids)","start":{"date-parts":[[2018,11,6]]},"location":"Beijing, China","end":{"date-parts":[[2018,11,9]]}},"container-title":["2018 IEEE-RAS 18th International Conference on Humanoid Robots (Humanoids)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8596719\/8624912\/08624972.pdf?arnumber=8624972","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,26]],"date-time":"2022-01-26T23:10:20Z","timestamp":1643238620000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8624972\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,11]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/humanoids.2018.8624972","relation":{},"subject":[],"published":{"date-parts":[[2018,11]]}}}