{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,14]],"date-time":"2026-03-14T20:59:32Z","timestamp":1773521972855,"version":"3.50.1"},"reference-count":36,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2016,10]]},"DOI":"10.1109\/iros.2016.7759578","type":"proceedings-article","created":{"date-parts":[[2016,12,19]],"date-time":"2016-12-19T21:08:02Z","timestamp":1482181682000},"page":"3928-3934","source":"Crossref","is-referenced-by-count":79,"title":["Stable reinforcement learning with autoencoders for tactile and visual data"],"prefix":"10.1109","author":[{"given":"Herke","family":"van Hoof","sequence":"first","affiliation":[]},{"given":"Nutan","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Maximilian","family":"Karl","sequence":"additional","affiliation":[]},{"given":"Patrick","family":"van der Smagt","sequence":"additional","affiliation":[]},{"given":"Jan","family":"Peters","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref33","article-title":"Deep Kalman filters","author":"krishnan","year":"2015","journal-title":"NIPS Advances in Variational Inference Workshop"},{"key":"ref32","first-page":"2728","article-title":"Embed to control: A locally linear latent dynamics model for control from raw images","author":"watter","year":"2015","journal-title":"NIPS"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.2174\/1573399812666160613113556"},{"key":"ref30","article-title":"Trust region policy optimization","author":"schulman","year":"2015","journal-title":"ICML"},{"key":"ref36","first-page":"1177","article-title":"Random features for large-scale kernel machines","author":"rahimi","year":"2007","journal-title":"NIPS"},{"key":"ref35","article-title":"Covariant policy search","author":"bagnell","year":"2003","journal-title":"International Joint Conference on ArtificalIntelligence"},{"key":"ref34","doi-asserted-by":"crossref","first-page":"1607","DOI":"10.1609\/aaai.v24i1.7727","article-title":"Relative entropy policy search","author":"peters","year":"2010","journal-title":"AAAI"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-36434-X_5"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2014.6943031"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2010.06.001"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2011.5980200"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2008.4650953"},{"key":"ref15","article-title":"Learning of non-parametric control policies with high-dimensional state features","author":"van hoof","year":"2015","journal-title":"AISTATS"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/HUMANOIDS.2015.7363524"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390294"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1561\/2200000006"},{"key":"ref19","article-title":"Auto-encoding variational Bayes","author":"kingma","year":"2014","journal-title":"ICLRE"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/2463372.2463509"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7139389"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2013.6707053"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/70.880799"},{"key":"ref29","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2015","journal-title":"arXiv Tech Rep 1509 02971"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2011.6095096"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2010.5649494"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2014.6907803"},{"key":"ref2","doi-asserted-by":"crossref","DOI":"10.1613\/jair.301","article-title":"Reinforcement learning: A survey","volume":"4","author":"kaelbling","year":"1996","journal-title":"J Artificial Intell Research"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/HUMANOIDS.2012.6651537"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913495721"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/HUMANOIDS.2015.7363570"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487173"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-34500-5_16"},{"key":"ref24","first-page":"1502.02251","article-title":"From pixels to torques: Policy learning with deep dynamical models","author":"wahlstr\u00f6m","year":"2015","journal-title":"arXiv Tech Rep"},{"key":"ref23","article-title":"Data-efficient learning of feedback policies from image pixels using deep dynamical models","author":"assael","year":"2015","journal-title":"arXiv Tech Rep"},{"key":"ref26","article-title":"Neural fitted Q iteration—first experiences with a data efficient neural reinforcement learning method","author":"riedmiller","year":"2005","journal-title":"ECML"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2012.6252823"}],"event":{"name":"2016 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","location":"Daejeon, South Korea","start":{"date-parts":[[2016,10,9]]},"end":{"date-parts":[[2016,10,14]]}},"container-title":["2016 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7743711\/7758082\/07759578.pdf?arnumber=7759578","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,13]],"date-time":"2025-06-13T19:06:21Z","timestamp":1749841581000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7759578\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,10]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/iros.2016.7759578","relation":{},"subject":[],"published":{"date-parts":[[2016,10]]}}}