{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T13:24:58Z","timestamp":1778246698440,"version":"3.51.4"},"reference-count":36,"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":["CPS\u20131739964,IIS-1724157,NRI-1925082"],"award-info":[{"award-number":["CPS\u20131739964,IIS-1724157,NRI-1925082"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000006","name":"ONR","doi-asserted-by":"publisher","award":["N00014-18-2243"],"award-info":[{"award-number":["N00014-18-2243"]}],"id":[{"id":"10.13039\/100000006","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000183","name":"ARO","doi-asserted-by":"publisher","award":["W911NF-19-2-0333"],"award-info":[{"award-number":["W911NF-19-2-0333"]}],"id":[{"id":"10.13039\/100000183","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\/icra46639.2022.9811570","type":"proceedings-article","created":{"date-parts":[[2022,7,12]],"date-time":"2022-07-12T19:36:40Z","timestamp":1657654600000},"page":"2452-2458","source":"Crossref","is-referenced-by-count":10,"title":["Adversarial Imitation Learning from Video Using a State Observer"],"prefix":"10.1109","author":[{"given":"Haresh","family":"Karnan","sequence":"first","affiliation":[{"name":"University of Texas,Department of Mechanical Engineering,Austin,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Faraz","family":"Torabi","sequence":"additional","affiliation":[{"name":"University of Texas,Department of Computer Science,Austin,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Garrett","family":"Warnell","sequence":"additional","affiliation":[{"name":"Army Research Laboratory,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peter","family":"Stone","sequence":"additional","affiliation":[{"name":"University of Texas,Department of Computer Science,Austin and Sony AI,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","author":"kostrikov","year":"2018","journal-title":"Pytorch implementations of reinforcement learning algorithms"},{"key":"ref32","article-title":"Proximal policy optimization algorithms","volume":"abs 1707 6347","author":"schulman","year":"2017","journal-title":"CoRR"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref30","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":"ref36","article-title":"Image augmentation is all you need: Regularizing deep reinforcement learning from pixels","volume":"abs 2004 13649","author":"kostrikov","year":"2020","journal-title":"CoRR"},{"key":"ref35","article-title":"Reinforcement learning with augmented data","volume":"abs 2004 14990","author":"laskin","year":"2020","journal-title":"CoRR"},{"key":"ref34","article-title":"Combining model-based and model-free updates for trajectory-centric reinforcement learning","volume":"abs 1703 3078","author":"chebotar","year":"2017","journal-title":"CoRR"},{"key":"ref10","article-title":"Reinforcement learning with videos: Combining offline observations with interaction","volume":"abs 2011 6507","author":"schmeckpeper","year":"2020","journal-title":"CoRR"},{"key":"ref11","article-title":"Third-person imitation learning","volume":"abs 1703 1703","author":"stadie","year":"2017","journal-title":"CoRR"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref13","author":"brockman","year":"2016","journal-title":"OpenAI Gym"},{"key":"ref14","first-page":"15","article-title":"A framework for behavioural cloning","author":"bain","year":"1995","journal-title":"Machine Intelligence"},{"key":"ref15","author":"ross","year":"2011","journal-title":"A reduction of imitation learning and structured prediction to no-regret online learning"},{"key":"ref16","author":"daftry","year":"2016","journal-title":"Learning transferable policies for monocular reactive mav control"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8462891"},{"key":"ref18","first-page":"1153","article-title":"Boosting structured prediction for imitation learning","author":"ratliff","year":"2006","journal-title":"Proceedings of the 19th International Conference on Neural Information Processing Systems ser NIPS'06"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.cognition.2009.07.005"},{"key":"ref28","first-page":"12402","article-title":"Off-policy imitation learning from observations","volume":"33","author":"zhu","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/497"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8462891"},{"key":"ref3","author":"torabi","year":"2019","journal-title":"Generative adversarial imitation from observation"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/882"},{"key":"ref29","author":"hudson","year":"2021","journal-title":"Rail A modular framework for reinforcement-learning-based adversarial imitation learning"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/687"},{"key":"ref8","article-title":"Imitation from observation: Learning to imitate behaviors from raw video via context translation","volume":"abs 1707 3374","author":"liu","year":"2017","journal-title":"CoRR"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636169"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2008.10.024"},{"key":"ref9","article-title":"Imitating latent policies from observation","volume":"abs 1805 7914","author":"edwards","year":"2018","journal-title":"CoRR"},{"key":"ref1","first-page":"1040","article-title":"Learning from demonstration","author":"schaal","year":"1996","journal-title":"Proceedings of the 9th International Conference on Neural Information Processing Systems ser NIPS'96"},{"key":"ref20","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref22","author":"kostrikov","year":"2019","journal-title":"Imitation learning via off-policy distribution matching"},{"key":"ref21","article-title":"Generative adversarial imitation learning","volume":"abs 1606 3476","author":"ho","year":"2016","journal-title":"CoRR"},{"key":"ref24","author":"goodfellow","year":"2014","journal-title":"Generative adversarial networks"},{"key":"ref23","article-title":"Primal wasserstein imitation learning","volume":"abs 2006 4678","author":"dadashi","year":"2020","journal-title":"CoRR"},{"key":"ref26","first-page":"661","article-title":"Efficient reductions for imitation learning","volume":"9","author":"ross","year":"2010","journal-title":"Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics ser Proceedings of Machine Learning Research"},{"key":"ref25","first-page":"103","article-title":"A framework for behavioural cloning","author":"bain","year":"1995","journal-title":"Machine Intelligence 15"}],"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\/09811570.pdf?arnumber=9811570","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,3]],"date-time":"2022-11-03T23:07:13Z","timestamp":1667516833000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9811570\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/icra46639.2022.9811570","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}