{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,25]],"date-time":"2026-10-25T14:06:25Z","timestamp":1792937185839,"version":"4.5.0"},"reference-count":26,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2016,5]]},"DOI":"10.1109\/icra.2016.7487156","type":"proceedings-article","created":{"date-parts":[[2016,6,9]],"date-time":"2016-06-09T21:33:24Z","timestamp":1465508004000},"page":"378-383","source":"Crossref","is-referenced-by-count":143,"title":["Optimal control with learned local models: Application to dexterous manipulation"],"prefix":"10.1109","author":[{"given":"Vikash","family":"Kumar","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Emanuel","family":"Todorov","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sergey","family":"Levine","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2004.1389841"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2010.VI.005"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2009.5152385"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2011.VII.008"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913495721"},{"key":"ref15","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":"ref16","article-title":"Sample-based information-theoretic stochastic optimal control","author":"lioutikov","year":"2014","journal-title":"International Conference on Robotics and Automation (ICRA)"},{"key":"ref17","first-page":"222","article-title":"Iterative linear quadratic regulator design for nonlinear biological movement systems","author":"li","year":"2004","journal-title":"ICINCO (1)"},{"key":"ref18","article-title":"Guided policy search","author":"levine","year":"2013","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref19","article-title":"Covariant policy search","author":"bagnell","year":"2003","journal-title":"International Joint Conference on Artificial Intelligence (IJCAI)"},{"key":"ref4","author":"sutton","year":"1998","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.45.8.1288"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1994.6.2.215"},{"key":"ref8","doi-asserted-by":"crossref","first-page":"65","DOI":"10.1007\/978-3-642-05181-4_4","article-title":"Adaptive optimal feedback control with learned internal dynamics models","volume":"264","author":"mitrovic","year":"2010","journal-title":"From Motor Learning to Interaction Learning in Robots"},{"key":"ref7","author":"\u00e5str\u00f6m","year":"2013","journal-title":"Adaptive control Courier Corporation"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2013.6630771"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7138994"},{"key":"ref1","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":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2008.02.003"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511804441"},{"key":"ref21","article-title":"Relative entropy policy search","author":"peters","year":"0","journal-title":"AAAI Conference on Artificial Intelligence 2010"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2011.2171093"},{"key":"ref26","article-title":"End-to-end training of deep visuomotor policies","author":"levine","year":"2015","journal-title":"arXiv preprint arXiv 1504 00702"},{"key":"ref25","article-title":"Nonparametric representation of policies and value functions: A trajectory-based approach","author":"atkeson","year":"0","journal-title":"Advances in Neural Information Processing Systems (NIPS) 2002"}],"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\/07487156.pdf?arnumber=7487156","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,6,24]],"date-time":"2017-06-24T16:03:43Z","timestamp":1498320223000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7487156\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,5]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/icra.2016.7487156","relation":{},"subject":[],"published":{"date-parts":[[2016,5]]}}}