{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T16:55:21Z","timestamp":1730220921445,"version":"3.28.0"},"reference-count":26,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,7,1]],"date-time":"2019-07-01T00:00:00Z","timestamp":1561939200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,7,1]],"date-time":"2019-07-01T00:00:00Z","timestamp":1561939200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,7,1]],"date-time":"2019-07-01T00:00:00Z","timestamp":1561939200000},"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":[[2019,7]]},"DOI":"10.1109\/eurocon.2019.8861589","type":"proceedings-article","created":{"date-parts":[[2019,10,10]],"date-time":"2019-10-10T23:21:33Z","timestamp":1570749693000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["Learning of Robotic Throwing at a Target using a Qualitative Learning Reward"],"prefix":"10.1109","author":[{"given":"Zvezdan","family":"Loncarevic","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rok","family":"Pahic","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mihael","family":"Simonic","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ales","family":"Ude","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andrej","family":"Gams","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.3389\/frobt.2018.00077"},{"key":"ref11","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)"},{"journal-title":"Theory and Application of Reward Shaping in Reinforcement Learning","year":"2004","author":"laud","key":"ref12"},{"key":"ref13","first-page":"663","article-title":"Algorithms for inverse reinforcement learning","author":"ng","year":"2000","journal-title":"ICML Machine Learning Proceedings of the Seventh International Conference"},{"key":"ref14","article-title":"A survey of inverse reinforcement learning: Challenges, methods and progress","volume":"abs 1806 6877","author":"arora","year":"2018","journal-title":"CoRR"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2015.09.011"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-011-9234-3"},{"key":"ref17","article-title":"Deep reinforcement learning from human preferences","author":"christiano","year":"2017","journal-title":"arXiv preprint arXiv 1706 03741"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2017.XIII.053"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/1597735.1597738"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2008.2006703"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/S1364-6613(99)01327-3"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1080\/01691864.2013.814211"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2008.10.024"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-010-5223-6"},{"key":"ref7","first-page":"1238","author":"kober","year":"2013","journal-title":"Reinforcement Learning in Robotics A Survey"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2860628"},{"key":"ref9","first-page":"388","author":"deisenroth","year":"2013","journal-title":"A Survey on Policy Search for Robotics"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2010.2065430"},{"key":"ref20","first-page":"1","article-title":"Reinforcement learning combined with human feedback in continuous state and action spaces","author":"vien","year":"2012","journal-title":"IEEE International Conference on Development and Learning and Epigenetic Robotics (ICDL)"},{"key":"ref22","article-title":"Investigating human priors for playing video games","volume":"abs 1802 10217","author":"dubey","year":"2018","journal-title":"CoRR"},{"key":"ref21","first-page":"1503","article-title":"Programming by Feedback","author":"akrour","year":"2014","journal-title":"International Conference on Machine Learning no 32 in JMLR Proceedings"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2011.07.004"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1162\/NECO_a_00393"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICHR.2010.5686841"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/Humanoids.2011.6100913"}],"event":{"name":"IEEE EUROCON 2019 -18th International Conference on Smart Technologies","start":{"date-parts":[[2019,7,1]]},"location":"Novi Sad, Serbia","end":{"date-parts":[[2019,7,4]]}},"container-title":["IEEE EUROCON 2019 -18th International Conference on Smart Technologies"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8852488\/8861510\/08861589.pdf?arnumber=8861589","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,17]],"date-time":"2022-07-17T21:51:19Z","timestamp":1658094679000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8861589\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,7]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/eurocon.2019.8861589","relation":{},"subject":[],"published":{"date-parts":[[2019,7]]}}}