{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,24]],"date-time":"2026-10-24T17:10:04Z","timestamp":1792861804810,"version":"4.5.0"},"reference-count":38,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2016,5]]},"DOI":"10.1109\/icra.2016.7487173","type":"proceedings-article","created":{"date-parts":[[2016,6,9]],"date-time":"2016-06-09T17:33:24Z","timestamp":1465493604000},"page":"512-519","source":"Crossref","is-referenced-by-count":260,"title":["Deep spatial autoencoders for visuomotor learning"],"prefix":"10.1109","author":[{"given":"Chelsea","family":"Finn","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"family":"Xin Yu Tan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"family":"Yan Duan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Trevor","family":"Darrell","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sergey","family":"Levine","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pieter","family":"Abbeel","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref38","article-title":"Agnostic system identification for model-based reinforcement learning","author":"ross","year":"2012","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref33","article-title":"Covariant policy search","author":"bagnell","year":"2003","journal-title":"International Joint Conference on Artificial Intelligence (IJCAI)"},{"key":"ref32","article-title":"Iterative linear quadratic regulator design for nonlinear biological movement systems","author":"li","year":"2004","journal-title":"ICINCO"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1561\/2300000021"},{"key":"ref30","article-title":"Stacked what-where auto-encoders","author":"zhao","year":"0","journal-title":"arXiv preprint arXiv 1506 00747 2015"},{"key":"ref37","article-title":"ImageNet: A large-scale hierarchical image database","author":"deng","year":"2009","journal-title":"Computer Vision and Pattern Recognition (CVPR)"},{"key":"ref36","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"2015","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref35","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v24i1.7727","article-title":"Relative entropy policy search","author":"peters","year":"2010","journal-title":"AAAI Conference on Artificial Intelligence"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2008.02.003"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2011.VII.008"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2009.5152385"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1177\/0278364907084980"},{"key":"ref13","article-title":"Fast biped walking with a reflexive controller and realtime policy searching","author":"geng","year":"2006","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2004.1307456"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2004.1389841"},{"key":"ref16","first-page":"1063","article-title":"Reinforcement learning with factored states and actions","volume":"5","author":"sallans","year":"2004","journal-title":"J Machine Learning Research (JMLR)"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-377-6.50013-X"},{"key":"ref18","article-title":"Learning predictive state representations","author":"singh","year":"2003","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1177\/0278364911404092"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.1994.350995"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2013.6707053"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.1997.606723"},{"key":"ref3","article-title":"Embed to control: A locally linear latent dynamics model for control from raw images","author":"watter","year":"0","journal-title":"Advances in Neural Information Processing Systems (NIPS) 2015"},{"key":"ref6","article-title":"Sparse deep belief net model for visual area V2","author":"lee","year":"2008","journal-title":"Neural Information Processing Systems (NIPS)"},{"key":"ref29","article-title":"Going deeper with convolutions","author":"szegedy","year":"0","journal-title":"arXiv preprint arXiv 1409 4842 2014"},{"key":"ref5","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"lecun","year":"2015","journal-title":"Nature"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7138994"},{"key":"ref7","article-title":"Learning neural network policies with guided policy search under unknown dynamics","author":"levine","year":"0","journal-title":"Advances in Neural Information Processing Systems (NIPS) 2014"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2014.X.019"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2010.VI.005"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2012.6252823"},{"key":"ref20","article-title":"Autonomous learning of state representations for control","author":"b\u00f6hmer","year":"0","journal-title":"KI - Knstliche Intelligenz 2015"},{"key":"ref22","article-title":"Playing Atari with deep reinforcement learning","author":"mnih","year":"0","journal-title":"NIPS Deep Learning Workshop 2013"},{"key":"ref21","article-title":"Learning to linearize under uncertainty","author":"goroshin","year":"0","journal-title":"arXiv preprint arXiv 1506 00747 2015"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/70.143350"},{"key":"ref23","article-title":"End-to-end training of deep visuomotor policies","author":"levine","year":"0","journal-title":"arXiv preprint arXiv 1504 01039 2015"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/70.538974"},{"key":"ref25","article-title":"Vision based control of a quadrotor for perching on planes and lines","author":"mohta","year":"2014","journal-title":"International Conference on Robotics and Automation (ICRA)"}],"event":{"name":"2016 IEEE International Conference on Robotics and Automation (ICRA)","location":"Stockholm, Sweden","start":{"date-parts":[[2016,5,16]]},"end":{"date-parts":[[2016,5,21]]}},"container-title":["2016 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7478842\/7487087\/07487173.pdf?arnumber=7487173","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,17]],"date-time":"2024-06-17T09:38:02Z","timestamp":1718617082000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7487173\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,5]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/icra.2016.7487173","relation":{},"subject":[],"published":{"date-parts":[[2016,5]]}}}