{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T13:56:29Z","timestamp":1773842189870,"version":"3.50.1"},"reference-count":30,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2015,5]]},"DOI":"10.1109\/icra.2015.7138994","type":"proceedings-article","created":{"date-parts":[[2015,7,6]],"date-time":"2015-07-06T21:20:30Z","timestamp":1436217630000},"page":"156-163","source":"Crossref","is-referenced-by-count":183,"title":["Learning contact-rich manipulation skills with guided policy search"],"prefix":"10.1109","author":[{"given":"Sergey","family":"Levine","sequence":"first","affiliation":[]},{"given":"Nolan","family":"Wagener","sequence":"additional","affiliation":[]},{"given":"Pieter","family":"Abbeel","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref30","article-title":"Exploring deep and recurrent architectures for optimal control","author":"levine","year":"2013","journal-title":"NIPS Deep Learning Workshop 2013"},{"key":"ref10","article-title":"Learning attractor landscapes for learning motor primitives","author":"ijspeert","year":"2003","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"ref11","article-title":"Reinforcement learning to adjust robot movements to new situations","author":"kober","year":"2010","journal-title":"Robotics Science and Systems"},{"key":"ref12","article-title":"Learning to control a low-cost manipulator using data-efficient reinforcement learning","author":"deisenroth","year":"2011","journal-title":"Robotics Science and Systems"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2011.6095096"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2011.5980200"},{"key":"ref15","doi-asserted-by":"crossref","first-page":"1521","DOI":"10.1163\/156855307782148550","article-title":"Reinforcement learning for imitating constrained reaching movements","volume":"21","author":"guenter","year":"2007","journal-title":"Advanced Robotics"},{"key":"ref16","article-title":"Reinforcement learning of motor skills in high dimensions","author":"theodorou","year":"2010","journal-title":"International Conference on Robotics and Automation (ICRA)"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2007.363631"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.1992.220143"},{"key":"ref19","article-title":"Guided policy search","author":"levine","year":"2013","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511804441"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2004.1307456"},{"key":"ref27","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":"ref3","doi-asserted-by":"publisher","DOI":"10.1561\/2300000021"},{"key":"ref6","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":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2010.5510001"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2004.1389841"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2008.02.003"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1177\/0278364907084980"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913495721"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2009.5152385"},{"key":"ref1","article-title":"Learning neural network policies with guided policy search under unknown dynamics","author":"levine","year":"2014","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"ref20","article-title":"Variational policy search via trajectory optimization","author":"levine","year":"2013","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"ref22","doi-asserted-by":"crossref","DOI":"10.15607\/RSS.2014.X.052","article-title":"Combining the benefits of function approximation and trajectory optimization","author":"mordatch","year":"2014","journal-title":"Robotics Science and Systems (RSS)"},{"key":"ref21","article-title":"Learning complex neural network policies with trajectory optimization","author":"levine","year":"2014","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref24","first-page":"627","article-title":"A reduction of imitation learning and structured prediction to no-regret online learning","volume":"15","author":"ross","year":"2011","journal-title":"Journal of Machine Learning Research"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/MCS.2006.1636313"},{"key":"ref26","article-title":"Covariant policy search","author":"bagnell","year":"2003","journal-title":"International Joint Conference on Artificial Intelligence (IJCAI)"},{"key":"ref25","article-title":"Sample-based information-theoretic stochastic optimal control","author":"lioutikov","year":"2014","journal-title":"International Conference on Robotics and Automation (ICRA)"}],"event":{"name":"2015 IEEE International Conference on Robotics and Automation (ICRA)","location":"Seattle, WA, USA","start":{"date-parts":[[2015,5,26]]},"end":{"date-parts":[[2015,5,30]]}},"container-title":["2015 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7128761\/7138973\/07138994.pdf?arnumber=7138994","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,12]],"date-time":"2023-08-12T02:12:32Z","timestamp":1691806352000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7138994\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,5]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/icra.2015.7138994","relation":{},"subject":[],"published":{"date-parts":[[2015,5]]}}}