{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,25]],"date-time":"2026-09-25T06:49:41Z","timestamp":1790318981241,"version":"4.1.0"},"reference-count":36,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,11,1]],"date-time":"2019-11-01T00:00:00Z","timestamp":1572566400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,11,1]],"date-time":"2019-11-01T00:00:00Z","timestamp":1572566400000},"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":[[2019,11]]},"DOI":"10.1109\/iros40897.2019.8968063","type":"proceedings-article","created":{"date-parts":[[2020,1,30]],"date-time":"2020-01-30T23:53:51Z","timestamp":1580428431000},"page":"1812-1817","source":"Crossref","is-referenced-by-count":20,"title":["Learning Virtual Grasp with Failed Demonstrations via Bayesian Inverse Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Xu","family":"Xie","sequence":"first","affiliation":[{"name":"UCLA Center for Vision, Cognition, Learning, and Autonomy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Changyang","family":"Li","sequence":"additional","affiliation":[{"name":"UCLA Center for Vision, Cognition, Learning, and Autonomy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chi","family":"Zhang","sequence":"additional","affiliation":[{"name":"UCLA Center for Vision, Cognition, Learning, and Autonomy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yixin","family":"Zhu","sequence":"additional","affiliation":[{"name":"UCLA Center for Vision, Cognition, Learning, and Autonomy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Song-Chun","family":"Zhu","sequence":"additional","affiliation":[{"name":"UCLA Center for Vision, Cognition, Learning, and Autonomy"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794230"},{"key":"ref32","article-title":"Benchmarking deep reinforcement learning for continuous control","author":"duan","year":"2016","journal-title":"ICML"},{"key":"ref31","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref30","article-title":"Towards vision-based deep reinforcement learning for robotic motion control","author":"zhang","year":"2015","journal-title":"arXiv preprint arXiv 1511 05271"},{"key":"ref36","article-title":"Semi-supervised support vector machines","author":"bennett","year":"1999","journal-title":"NIPS"},{"key":"ref35","article-title":"Semi-supervised apprenticeship learning","author":"valko","year":"2013","journal-title":"Proc of European Workshop on Reinforcement Learning"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018025"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390175"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2008.IV.034"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/1538788.1538812"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-009-9121-3"},{"key":"ref14","article-title":"Analysis of inverse reinforcement learning with perturbed demonstrations","author":"melo","year":"2010","journal-title":"ECAI"},{"key":"ref15","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v28i1.8979","article-title":"Robust bayesian inverse reinforcement learning with sparse behavior noise","author":"zheng","year":"2014","journal-title":"AAAI"},{"key":"ref16","author":"ziebart","year":"2010","journal-title":"Modeling Purposeful Adaptive Behavior with the Principle of Maximum Causal Entropy"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487168"},{"key":"ref18","article-title":"Reinforcement learning from imperfect demonstrations","author":"gao","year":"2018","journal-title":"arXiv preprint arxiv 1802 05807"},{"key":"ref19","article-title":"Algorithms for inverse reinforcement learning","author":"ng","year":"2000","journal-title":"ICML"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1177\/027836499601500302"},{"key":"ref4","article-title":"Inverse reinforcement learning from failure","author":"shiarlis","year":"2016","journal-title":"AAMAS"},{"key":"ref27","article-title":"Inverse reinforcement learning via deep gaussian process","author":"jin","year":"2015","journal-title":"arXiv preprint arXiv 1512 08571"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2016.7759575"},{"key":"ref6","article-title":"Deep imitation learning for complex manipulation tasks from virtual reality teleoperation","author":"zhang","year":"2017","journal-title":"arXiv preprint arXiv 1710 04615"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2011.07.016"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3321408.3322633"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2016.XII.033"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2008.10.024"},{"key":"ref2","author":"puterman","year":"2014","journal-title":"Markov Decision Processes Discrete Stochastic Dynamic Programming"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202137"},{"key":"ref1","article-title":"Learning agents for uncertain environments","author":"russell","year":"1998","journal-title":"ICML"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1561\/2300000053"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/1015330.1015430"},{"key":"ref21","article-title":"A survey of inverse reinforcement learning: Challenges, methods and progress","author":"arora","year":"2018","journal-title":"arXiv Preprint arXiv 1806 06877"},{"key":"ref24","first-page":"1","article-title":"Bayesian inverse reinforcement learning","volume":"51","author":"ramachandran","year":"2007","journal-title":"Urbana"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143936"},{"key":"ref26","article-title":"Nonlinear inverse reinforcement learning with gaussian processes","author":"levine","year":"2011","journal-title":"NIPS"},{"key":"ref25","article-title":"Maximum entropy inverse reinforcement learning","author":"ziebart","year":"2008","journal-title":"AAAI"}],"event":{"name":"2019 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","location":"Macau, China","start":{"date-parts":[[2019,11,3]]},"end":{"date-parts":[[2019,11,8]]}},"container-title":["2019 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8957008\/8967518\/08968063.pdf?arnumber=8968063","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,26]],"date-time":"2025-08-26T21:54:35Z","timestamp":1756245275000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8968063\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,11]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/iros40897.2019.8968063","relation":{},"subject":[],"published":{"date-parts":[[2019,11]]}}}