{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:57:49Z","timestamp":1777658269839,"version":"3.51.4"},"reference-count":38,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2023,2,1]],"date-time":"2023-02-01T00:00:00Z","timestamp":1675209600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,2,1]],"date-time":"2023-02-01T00:00:00Z","timestamp":1675209600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,2,1]],"date-time":"2023-02-01T00:00:00Z","timestamp":1675209600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100000038","name":"Natural Sciences and Engineering Research Council of Canada","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000038","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Robot."],"published-print":{"date-parts":[[2023,2]]},"DOI":"10.1109\/tro.2022.3192969","type":"journal-article","created":{"date-parts":[[2022,8,9]],"date-time":"2022-08-09T20:38:51Z","timestamp":1660077531000},"page":"681-698","source":"Crossref","is-referenced-by-count":5,"title":["Joint Estimation of Expertise and Reward Preferences From Human Demonstrations"],"prefix":"10.1109","volume":"39","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6026-0635","authenticated-orcid":false,"given":"Pamela","family":"Carreno-Medrano","sequence":"first","affiliation":[{"name":"Faculty of Engineering, Monash University, Melbourne, VIC, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8636-407X","authenticated-orcid":false,"given":"Stephen L.","family":"Smith","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Faculty of Engineering, University of Waterloo, Waterloo, ON, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4169-2141","authenticated-orcid":false,"given":"Dana","family":"Kulic","sequence":"additional","affiliation":[{"name":"Faculty of Engineering, Monash University, Melbourne, VIC, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989466"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1177\/0278364915619772"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-100819-063206"},{"key":"ref4","first-page":"189","article-title":"Efficient model learning from joint-action demonstrations for human-robot collaborative tasks","volume-title":"Proc. 10th ACM\/IEEE Int. Conf. HumanRobot Interact.","author":"Nikolaidis","year":"2015"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2020.2971415"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1177\/0278364920910802"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-018-9746-1"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2926963"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/RO-MAN47096.2020.9223430"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v28i1.8979"},{"key":"ref11","article-title":"Human irrationality: Both bad and good for reward inference","author":"Chan","year":"2021","journal-title":"arXiv:2111.06956"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s11336-017-9570-0"},{"key":"ref13","first-page":"1255","article-title":"Modeling interaction via the principle of maximum causal entropy","volume-title":"Proc. 27th Int. Conf. Int. Conf. Mach. Learn.","author":"Ziebart","year":"2010"},{"key":"ref14","article-title":"If MaxEnt RL is the answer, what is the question?","author":"Eysenbach","year":"2019"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/RO-MAN46459.2019.8956320"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2017.XIII.053"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2021.103500"},{"key":"ref18","first-page":"4299","article-title":"Deep reinforcement learning from human preferences","volume":"30","author":"Christiano","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref19","first-page":"369","article-title":"Active preference-based Gaussian process regression for reward learning","volume-title":"Proc. Robot.: Sci. Syst.","author":"Byk","year":"2020"},{"key":"ref20","first-page":"4415","article-title":"Reward-rational (implicit) choice: A unifying formalism for reward learning","volume-title":"Proc. 34th Int. Conf. Neural Inf. Process. Syst.","author":"Jeon","year":"2020"},{"key":"ref21","first-page":"1177","article-title":"Asking easy questions: A user-friendly approach to active reward learning","volume-title":"Proc. Conf. Robot Learn.","author":"Biyik","year":"2020"},{"key":"ref22","first-page":"783","article-title":"Extrapolating beyond suboptimal demonstrations via inverse reinforcement learning from observations","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","author":"Brown","year":"2019"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2897342"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-017-9675-4"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TBME.2006.881784"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989263"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/475"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/s11257-011-9106-8"},{"key":"ref29","first-page":"2586","article-title":"Bayesian inverse reinforcement learning","volume-title":"Proc. 20th Int. joint Conf. Artif. Intell.","author":"Ramachandran","year":"2007"},{"key":"ref30","first-page":"12340","article-title":"Confidence-aware imitation learning from demonstrations with varying optimality","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Zhang","year":"2021"},{"key":"ref31","volume-title":"The Intentional Stance","author":"Dennett","year":"1989"},{"key":"ref32","first-page":"1352","article-title":"Reinforcement learning with deep energy-based policies","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","author":"Haarnoja","year":"2017"},{"key":"ref33","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"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ROMAN.2018.8525546"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341530"},{"key":"ref36","first-page":"8026","article-title":"Pytorch: An imperative style, high-performance deep learning library","volume":"32","author":"Paszke","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref37","first-page":"19163","article-title":"Efficient planning in large MDPs with weak linear function approximation","volume-title":"Advances in Neural Information Processing Systems","volume":"33","author":"Shariff","year":"2020"},{"key":"ref38","first-page":"1165","article-title":"Safe imitation learning via fast Bayesian reward inference from preferences","volume-title":"Proc. 37th Int. Conf. Mach. Learn.","author":"Brown","year":"2020"}],"container-title":["IEEE Transactions on Robotics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8860\/10040949\/09852698.pdf?arnumber=9852698","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T12:13:16Z","timestamp":1706789596000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9852698\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,2]]},"references-count":38,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tro.2022.3192969","relation":{},"ISSN":["1552-3098","1941-0468"],"issn-type":[{"value":"1552-3098","type":"print"},{"value":"1941-0468","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,2]]}}}