{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T06:37:20Z","timestamp":1773902240129,"version":"3.50.1"},"reference-count":40,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,5]]},"DOI":"10.1109\/icra.2018.8462901","type":"proceedings-article","created":{"date-parts":[[2018,9,21]],"date-time":"2018-09-21T18:28:03Z","timestamp":1537554483000},"page":"1118-1125","source":"Crossref","is-referenced-by-count":157,"title":["Imitation from Observation: Learning to Imitate Behaviors from Raw Video via Context Translation"],"prefix":"10.1109","author":[{"given":"YuXuan","family":"Liu","sequence":"first","affiliation":[]},{"given":"Abhishek","family":"Gupta","sequence":"additional","affiliation":[]},{"given":"Pieter","family":"Abbeel","sequence":"additional","affiliation":[]},{"given":"Sergey","family":"Levine","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","author":"li","year":"2017","journal-title":"Inferring the latent structure of human decision-making from raw visual inputs"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref33","article-title":"Robobarista: Learning to manipulate novel objects via deep multimodal embedding","author":"sung","year":"2015","journal-title":"International Symposium on Robotics Research (ISRR)"},{"key":"ref32","article-title":"Deepmpc: Learning deep latent features for model predictive control","author":"lenz","year":"2015","journal-title":"Robot Sci Syst XI"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989307"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2014.6942916"},{"key":"ref37","article-title":"Mujoco: A physics engine for model-based control","author":"todorov","year":"2012","journal-title":"IROS"},{"key":"ref36","article-title":"Trust region policy optimization","author":"schulman","year":"2015","journal-title":"Proceedings of the ICML International Conference on Machine Learning"},{"key":"ref35","article-title":"Learning invariant feature spaces to transfer skills with reinforcement learning","author":"gupta","year":"2017","journal-title":"Proc Intl Conf on Learning Representations"},{"key":"ref34","article-title":"Se3-nets: Learning rigid body motion using deep neural networks","author":"byravan","year":"2017","journal-title":"ICRA"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/S1364-6613(99)01327-3"},{"key":"ref40","article-title":"Adapting deep visuomotor representations with weak pairwise constraints","author":"tzeng","year":"2016","journal-title":"Workshop on Algorithmic Robotics"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2008.10.024"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1177\/0278364910371999"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2009.5152577"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/S0921-8890(01)00155-5"},{"key":"ref15","doi-asserted-by":"crossref","DOI":"10.1145\/1015330.1015430","article-title":"Apprenticeship learning via inverse reinforcement learning","author":"abbeel","year":"2004","journal-title":"Proceedings of the twenty-first international conference on Machine learning"},{"key":"ref16","article-title":"Nonlinear inverse reinforcement learning with gaussian processes","author":"levine","year":"2011","journal-title":"Advances in Neural Information Processing Systems 24"},{"key":"ref17","article-title":"Maximum entropy inverse reinforcement learning","author":"ziebart","year":"2008","journal-title":"AAAI"},{"key":"ref18","article-title":"Maximum margin planning","author":"ratliff","year":"2006","journal-title":"Proceedings of the Twenty-Third International Conference on Machine Learning"},{"key":"ref19","article-title":"Bayesian inverse reinforcement learning","author":"ramachandran","year":"2007","journal-title":"IJCAI 2007 Proceedings of the 20th International Joint Conference on Artificial Intelligence"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.632"},{"key":"ref4","article-title":"ALVINN: an autonomous land vehicle in a neural network","author":"pomerleau","year":"1988","journal-title":"NIPS"},{"key":"ref27","article-title":"Unsupervised pixel-level domain adaptation with generative adversarial networks","author":"bousmalis","year":"2017","journal-title":"CVPR"},{"key":"ref3","article-title":"End-to-end training of deep visuomotor policies","volume":"17","author":"levine","year":"2016","journal-title":"J Mach Learn Res"},{"key":"ref6","article-title":"Algorithms for inverse reinforcement learning","author":"ng","year":"2000","journal-title":"Proc Seventh Int Conf Machine Learning"},{"key":"ref29","author":"gatys","year":"2015","journal-title":"A neural algorithm of artistic style"},{"key":"ref5","author":"edwards","year":"2016","journal-title":"Perceptual reward functions"},{"key":"ref8","article-title":"Generative adversarial imitation learning","author":"ho","year":"2016","journal-title":"Advances in Neural IInformation Processing Systems"},{"key":"ref7","article-title":"Third-person imitation learning","author":"stadie","year":"2017","journal-title":"Proc Intl Conf on Learning Representations"},{"key":"ref2","doi-asserted-by":"crossref","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2017.XIII.050"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2013.6630809"},{"key":"ref20","article-title":"Guided cost learning: Deep inverse optimal control via policy optimization","author":"finn","year":"2016","journal-title":"Proceedings of the 33nd ICML International Conference on Machine Learning"},{"key":"ref22","article-title":"Relative entropy inverse reinforcement learning","author":"boularias","year":"2011","journal-title":"Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2013.6630743"},{"key":"ref24","author":"lee","year":"2017","journal-title":"Learning robot activities from first-person human videos using convolutional future regression"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.69"},{"key":"ref26","article-title":"Unpaired image-to-image translation using cycle-consistent adversarial networks","author":"zhu","year":"2017","journal-title":"ICCV"},{"key":"ref25","article-title":"One-shot imitation learning","author":"duan","year":"2017","journal-title":"NIPS"}],"event":{"name":"2018 IEEE International Conference on Robotics and Automation (ICRA)","location":"Brisbane, QLD","start":{"date-parts":[[2018,5,21]]},"end":{"date-parts":[[2018,5,25]]}},"container-title":["2018 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8449910\/8460178\/08462901.pdf?arnumber=8462901","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,8,23]],"date-time":"2020-08-23T19:09:38Z","timestamp":1598209778000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8462901\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,5]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/icra.2018.8462901","relation":{},"subject":[],"published":{"date-parts":[[2018,5]]}}}