{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T17:41:25Z","timestamp":1776879685106,"version":"3.51.2"},"reference-count":40,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,10]]},"DOI":"10.1109\/iros.2018.8593951","type":"proceedings-article","created":{"date-parts":[[2019,1,24]],"date-time":"2019-01-24T02:33:30Z","timestamp":1548297210000},"page":"1577-1584","source":"Crossref","is-referenced-by-count":33,"title":["Learning Actionable Representations from Visual Observations"],"prefix":"10.1109","author":[{"given":"Debidatta","family":"Dwibedi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jonathan","family":"Tompson","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Corey","family":"Lynch","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pierre","family":"Sermanet","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref38","first-page":"527","article-title":"Shuffle and learn: unsupervised learning using temporal order verification","author":"misra","year":"2016","journal-title":"European Conference on Computer Vision"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref30","first-page":"4499","article-title":"Distral: Robust multitask reinforcement learning","author":"teh","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.1983.6313077"},{"key":"ref36","author":"finn","year":"0","journal-title":"Learning visual feature spaces for robotic manipulation with deep spatial autoencoders"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"ref34","first-page":"1857","article-title":"Improved deep metric learning with multi-class n-pair loss objective","author":"sohn","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref10","author":"brockman","year":"2016","journal-title":"OpenAI Gym"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-32375-1_2"},{"key":"ref11","first-page":"1089","article-title":"A physics-based model prior for object-oriented mdps","author":"scholz","year":"2014","journal-title":"International Conference on Machine Learning"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-015-9459-7"},{"key":"ref13","author":"lesort","year":"2017","journal-title":"Unsu-pervised state representation learning with robotic priors a robustness benchmark"},{"key":"ref14","first-page":"2746","article-title":"Embed to control: A locally linear latent dynamics model for control from raw images","author":"watter","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2016.7759578"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487173"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2016.7798980"},{"key":"ref18","first-page":"5074","article-title":"Learning to poke by poking: Experiential learning of intuitive physics","author":"agrawal","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref19","first-page":"3","article-title":"The curious robot: Learning visual representations via physical interactions","author":"pinto","year":"2016","journal-title":"European Conference on Computer Vision"},{"key":"ref4","author":"jonschkowski","year":"2017","journal-title":"Pves Position-velocity encoders for unsupervised learning of structured state representations"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989249"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8462891"},{"key":"ref27","author":"mirowski","year":"2016","journal-title":"Learning to navigate in complex environments"},{"key":"ref6","author":"tassa","year":"2018","journal-title":"Deepmind control suite"},{"key":"ref5","author":"schulman","year":"2017","journal-title":"Proximal policy optimization algorithms"},{"key":"ref29","author":"arora","year":"2018","journal-title":"Multi-task learning for continuous control"},{"key":"ref8","author":"lillicrap","year":"2015","journal-title":"Continuous control with deep reinforcement learning"},{"key":"ref7","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":"ref2","first-page":"740","article-title":"Microsoft coco: Common objects in context","author":"lin","year":"2014","journal-title":"European Conference on Computer Vision"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.002"},{"key":"ref22","first-page":"64","article-title":"Unsupervised learning for physical interaction through video prediction","author":"finn","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2018.00278"},{"key":"ref24","author":"dosovitskiy","year":"2016","journal-title":"Learning to act by predicting the future"},{"key":"ref23","author":"babaeizadeh","year":"2017","journal-title":"Stochastic variational video prediction"},{"key":"ref26","author":"jaderberg","year":"2016","journal-title":"Reinforcement learning with unsupervised auxiliary tasks"},{"key":"ref25","author":"shelhamer","year":"2016","journal-title":"Loss is its own reward Self-supervision for reinforcement learning"}],"event":{"name":"2018 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","location":"Madrid","start":{"date-parts":[[2018,10,1]]},"end":{"date-parts":[[2018,10,5]]}},"container-title":["2018 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8574473\/8593358\/08593951.pdf?arnumber=8593951","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,8,24]],"date-time":"2020-08-24T04:07:46Z","timestamp":1598242066000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8593951\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,10]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/iros.2018.8593951","relation":{},"subject":[],"published":{"date-parts":[[2018,10]]}}}