{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T14:24:08Z","timestamp":1768314248394,"version":"3.49.0"},"reference-count":41,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,6,3]],"date-time":"2024-06-03T00:00:00Z","timestamp":1717372800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,6,3]],"date-time":"2024-06-03T00:00:00Z","timestamp":1717372800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["2133027"],"award-info":[{"award-number":["2133027"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,6,3]]},"DOI":"10.1109\/ismr63436.2024.10585785","type":"proceedings-article","created":{"date-parts":[[2024,7,12]],"date-time":"2024-07-12T17:34:48Z","timestamp":1720805688000},"page":"1-7","source":"Crossref","is-referenced-by-count":9,"title":["Reward Learning from Suboptimal Demonstrations with Applications in Surgical Electrocautery"],"prefix":"10.1109","author":[{"given":"Zohre","family":"Karimi","sequence":"first","affiliation":[{"name":"Robotics Center and the Kahlert School of Computing at the University of Utah,Salt Lake City,UT,USA,84112"}]},{"given":"Shing-Hei","family":"Ho","sequence":"additional","affiliation":[{"name":"Robotics Center and the Kahlert School of Computing at the University of Utah,Salt Lake City,UT,USA,84112"}]},{"given":"Bao","family":"Thach","sequence":"additional","affiliation":[{"name":"Robotics Center and the Kahlert School of Computing at the University of Utah,Salt Lake City,UT,USA,84112"}]},{"given":"Alan","family":"Kuntz","sequence":"additional","affiliation":[{"name":"Robotics Center and the Kahlert School of Computing at the University of Utah,Salt Lake City,UT,USA,84112"}]},{"given":"Daniel S.","family":"Brown","sequence":"additional","affiliation":[{"name":"Robotics Center and the Kahlert School of Computing at the University of Utah,Salt Lake City,UT,USA,84112"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1186\/s12960-020-0448-3"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-062420-090543"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/iros45743.2020.9341382"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2008.10.024"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-100819-063206"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2021.103500"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ISMR48346.2021.9661514"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ISMR48346.2021.9661534"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2020.3045655"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196537"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CASE49439.2021.9551569"},{"key":"ref12","first-page":"783","article-title":"Extrapolating beyond suboptimal demonstrations via inverse reinforcement learning from observations","volume-title":"International conference on machine learning","author":"Brown"},{"key":"ref13","first-page":"10022","article-title":"Of moments and matching: A game-theoretic framework for closing the imitation gap","volume-title":"International Conference on Machine Learning","author":"Swamy"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989275"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636175"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561673"},{"issue":"136","key":"ref17","first-page":"1","article-title":"A survey of preference-based reinforcement learning methods","volume":"18","author":"Wirth","year":"2017","journal-title":"Journal of Ma-chine Learning Research"},{"key":"ref18","article-title":"Deep reinforcement learning from human preferences","volume":"30","author":"Christiano","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref19","first-page":"27730","article-title":"Training language models to follow instructions with human feedback","volume":"35","author":"Ouyang","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref20","article-title":"Causal confusion and reward misidentification in preference-based reward learning","volume-title":"The Eleventh International Conference on Learning Representations","author":"Tien","year":"2022"},{"key":"ref21","article-title":"Benchmarks and algorithms for offline preference-based reward learning","author":"Shin","year":"2023","journal-title":"arXiv preprint"},{"key":"ref22","first-page":"330","article-title":"Better-than-demonstrator imitation learning via automatically-ranked demonstrations","volume-title":"Conference on robot learning","author":"Brown"},{"issue":"89","key":"ref23","first-page":"15","article-title":"Electro surgical units-how they work and how to use them safely","volume":"28","author":"Cordero","year":"2015","journal-title":"Community eye health"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/0002-9610(94)90106-6"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.jocn.2012.10.032"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1038\/ajg.2009.105"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.jss.2017.06.093"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1177\/0278364918784350"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-27645-3_12"},{"key":"ref30","article-title":"Density- aware chamfer distance as a comprehensive metric for point cloud completion","author":"Wu","year":"2021","journal-title":"arXiv preprint"},{"key":"ref31","first-page":"29088","article-title":"Balanced chamfer distance as a comprehensive metric for point cloud completion","volume":"34","author":"Wu","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161081"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.amjsurg.2022.07.008"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1089\/end.2015.0191"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TMMS.1969.299896"},{"key":"ref36","first-page":"270","article-title":"Gpu-accelerated robotic simulation for distributed reinforce-ment learning","volume-title":"Conference on Robot Learning","author":"Liang"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2014.6907809"},{"key":"ref38","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"ar Xiv preprint"},{"key":"ref39","article-title":"Alvinn: An autonomous land vehicle in a neural network","volume":"1","author":"Pomerleau","year":"1988","journal-title":"Advances in neural information processing systems"},{"key":"ref40","first-page":"362","article-title":"Risk-aware active inverse reinforcement learning","volume-title":"Conference on Robot Learning","author":"Brown"},{"key":"ref41","article-title":"Asking easy questions: A user-friendly approach to active reward learning","volume-title":"Proceedings of the 3rd Con-ference on Robot Learning","author":"Biyik","year":"2019"}],"event":{"name":"2024 International Symposium on Medical Robotics (ISMR)","location":"Atlanta, GA, USA","start":{"date-parts":[[2024,6,3]]},"end":{"date-parts":[[2024,6,5]]}},"container-title":["2024 International Symposium on Medical Robotics (ISMR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10585266\/10585571\/10585785.pdf?arnumber=10585785","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,18]],"date-time":"2024-07-18T05:06:56Z","timestamp":1721279216000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10585785\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,3]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/ismr63436.2024.10585785","relation":{},"subject":[],"published":{"date-parts":[[2024,6,3]]}}}