{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,26]],"date-time":"2026-06-26T16:47:07Z","timestamp":1782492427646,"version":"3.54.5"},"reference-count":32,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017,9]]},"DOI":"10.1109\/iros.2017.8206046","type":"proceedings-article","created":{"date-parts":[[2017,12,14]],"date-time":"2017-12-14T22:12:59Z","timestamp":1513289579000},"page":"2351-2358","source":"Crossref","is-referenced-by-count":78,"title":["Deep predictive policy training using reinforcement learning"],"prefix":"10.1109","author":[{"given":"Ali","family":"Ghadirzadeh","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Atsuto","family":"Maki","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Danica","family":"Kragic","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marten","family":"Bjorkman","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref32","author":"jia","year":"2014","journal-title":"Caffe Convolutional Architecture for Fast Feature Embedding"},{"key":"ref31","first-page":"1889","article-title":"Trust region policy optimization","author":"schulman","year":"2015","journal-title":"ICML"},{"key":"ref30","article-title":"Benchmarking deep reinforcement learning for continuous control","author":"duan","year":"2016","journal-title":"ICML"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2015.12.271"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2016.7759578"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.2174\/1573399812666160613113556"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2015.7354076"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487178"},{"key":"ref15","doi-asserted-by":"crossref","first-page":"349","DOI":"10.1613\/jair.2110","article-title":"Closed-loop learning of visual control policies","volume":"28","author":"jodogne","year":"2007","journal-title":"Journal of Artificial Intelligence Research"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989384"},{"key":"ref17","article-title":"Learning to poke by poking: Experiential learning of intuitive physics","author":"agrawal","year":"2016","journal-title":"NIPS"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202141"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref28","article-title":"Auto-encoding variational Bayes","author":"kingma","year":"2014","journal-title":"ICLRE"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1037\/0033-295X.112.1.217"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2010.VI.005"},{"key":"ref3","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1561\/2300000021","article-title":"A survey on policy search for robotics","volume":"2","author":"deisenroth","year":"2013","journal-title":"Foundations and Trends in Robotics"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487173"},{"key":"ref29","author":"doersch","year":"2016","journal-title":"Tutorial on variational autoencoders"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2016.7759417"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2014.X.019"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2012.6252823"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913495721"},{"key":"ref9","article-title":"Embed to control: A locally linear latent dynamics model for control from raw images","author":"watter","year":"2015","journal-title":"NIPS"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/nrn3112"},{"key":"ref20","author":"lillicrap","year":"2015","journal-title":"Continuous control with deep reinforcement learning"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1137\/1.9780898718577"},{"key":"ref21","article-title":"Learning neural network policies with guided policy search under unknown dynamics","author":"levine","year":"2014","journal-title":"NIPS"},{"key":"ref24","article-title":"Gaussian process model based predictive control","author":"kocijan","year":"2004","journal-title":"ACC"},{"key":"ref23","author":"camacho","year":"2013","journal-title":"Model Predictive Control"},{"key":"ref26","article-title":"Policy search for motor primitives in robotics","author":"kober","year":"2009","journal-title":"NIPS"},{"key":"ref25","article-title":"Learning attractor landscapes for learning motor primitives","author":"ijspeert","year":"2003","journal-title":"NIPS"}],"event":{"name":"2017 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","location":"Vancouver, BC","start":{"date-parts":[[2017,9,24]]},"end":{"date-parts":[[2017,9,28]]}},"container-title":["2017 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8119304\/8202121\/08206046.pdf?arnumber=8206046","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,10,8]],"date-time":"2019-10-08T01:49:36Z","timestamp":1570499376000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/8206046\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,9]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/iros.2017.8206046","relation":{},"subject":[],"published":{"date-parts":[[2017,9]]}}}