{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,19]],"date-time":"2026-02-19T23:10:05Z","timestamp":1771542605106,"version":"3.50.1"},"reference-count":35,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"NSF","doi-asserted-by":"publisher","award":["1849952,1941722"],"award-info":[{"award-number":["1849952,1941722"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000006","name":"ONR","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000006","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,5,23]]},"DOI":"10.1109\/icra46639.2022.9811891","type":"proceedings-article","created":{"date-parts":[[2022,7,12]],"date-time":"2022-07-12T19:36:40Z","timestamp":1657654600000},"page":"441-447","source":"Crossref","is-referenced-by-count":5,"title":["Learning from Imperfect Demonstrations via Adversarial Confidence Transfer"],"prefix":"10.1109","author":[{"given":"Zhangjie","family":"Cao","sequence":"first","affiliation":[{"name":"Computer Science, Stanford University,CA,USA"}]},{"given":"Zihan","family":"Wang","sequence":"additional","affiliation":[{"name":"Computer Science, Stanford University,CA,USA"}]},{"given":"Dorsa","family":"Sadigh","sequence":"additional","affiliation":[{"name":"Computer Science, Stanford University,CA,USA"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00062"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460528"},{"key":"ref31","first-page":"23","article-title":"Domain randomization for transferring deep neural networks from sim-ulation to the real world","author":"tobin","year":"0","journal-title":"2017 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"},{"key":"ref30","author":"kim","year":"2019","journal-title":"Cross domain imitation learning"},{"key":"ref35","article-title":"Trust region policy optimization","author":"schulman","year":"2015","journal-title":"ICML"},{"key":"ref34","article-title":"Learning invariant feature spaces to transfer skills with reinforcement learning","author":"gupta","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref10","first-page":"330","article-title":"Better-than-demonstrator imitation learning via automatically-ranked demonstrations","author":"brown","year":"0","journal-title":"Conference on Robot Learning"},{"key":"ref11","article-title":"Learning from suboptimal demonstration via self-supervised reward regression","author":"chen","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref12","article-title":"Learning cross-domain correspondence for control with dynamics cycle-consistency","author":"zhang","year":"0","journal-title":"International Conference on Learning Representations"},{"key":"ref13","article-title":"A framework for behavioural cloning","author":"bain","year":"1995","journal-title":"Machine Intelligence 15"},{"key":"ref14","article-title":"Efficient reductions for imitation learning","author":"ross","year":"2010","journal-title":"AISTATS"},{"key":"ref15","article-title":"A reduction of imitation learning and structured prediction to no-regret online learning","author":"ross","year":"2011","journal-title":"AISTATS"},{"key":"ref16","first-page":"663","article-title":"Algorithms for inverse reinforcement learning","author":"ng","year":"2000","journal-title":"ICML"},{"key":"ref17","article-title":"Learning robust rewards with adverserial inverse reinforcement learning","author":"fu","year":"2018","journal-title":"ICLRE"},{"key":"ref18","article-title":"Wasserstein adversarial imitation learning","author":"xiao","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref19","article-title":"Deep bayesian reward learning from preferences","author":"brown","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-43089-4_44"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197197"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794310"},{"key":"ref3","article-title":"Generative adversarial imitation learning","volume":"29","author":"ho","year":"2016","journal-title":"NeurIPS"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3319502.3374832"},{"key":"ref29","article-title":"Unsupervised cross-domain transfer in policy gradient reinforcement learning via manifold alignment","volume":"29","author":"ammar","year":"0","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/4711.001.0001"},{"key":"ref8","article-title":"Confidence-aware imitation learning from demonstrations with varying optimality","author":"zhang","year":"0","journal-title":"Conference on Neural Information Processing Systems (NeurIPS)"},{"key":"ref7","article-title":"Imitation learning from imperfect demonstration","author":"wu","year":"2019","journal-title":"ICML"},{"key":"ref2","article-title":"Maximum entropy inverse reinforcement learning","author":"ziebart","year":"2008","journal-title":"AAAI"},{"key":"ref9","first-page":"783","article-title":"Extrapolating beyond suboptimal demonstrations via inverse reinforcement learning from observations","author":"brown","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/1015330.1015430"},{"key":"ref20","article-title":"Learning multimodal rewards from rankings","author":"myers","year":"0","journal-title":"Proceedings of the 5th Conference on Robot Learning (CoRL)"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3068912"},{"key":"ref21","first-page":"1029","article-title":"Dueling posterior sampling for preference-based reinforcement learning","author":"novoseller","year":"0","journal-title":"Conference on Uncertainty in Artificial Intelligence"},{"key":"ref24","doi-asserted-by":"crossref","DOI":"10.7551\/mitpress\/3676.003.0003","article-title":"The correspondence problem","volume":"41","author":"nehaniv","year":"2002","journal-title":"Imitation in Animals and Artifacts"},{"key":"ref23","article-title":"Learning feasibility to imitate demonstrators with different dynamics","author":"cao","year":"0","journal-title":"Proceedings of the 5th Conference on Robot Learning (CoRL)"},{"key":"ref26","article-title":"Cad2rl: Real single-image flight without a single real image","author":"sadeghi","year":"2016","journal-title":"ArXiv Preprint"},{"key":"ref25","article-title":"Transfer learning via inter-task mappings for temporal difference learning","volume":"8","author":"taylor","year":"2007","journal-title":"Journal of Machine Learning Research"}],"event":{"name":"2022 IEEE International Conference on Robotics and Automation (ICRA)","location":"Philadelphia, PA, USA","start":{"date-parts":[[2022,5,23]]},"end":{"date-parts":[[2022,5,27]]}},"container-title":["2022 International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9811522\/9811357\/09811891.pdf?arnumber=9811891","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,29]],"date-time":"2024-09-29T00:06:36Z","timestamp":1727568396000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9811891\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/icra46639.2022.9811891","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}