{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,19]],"date-time":"2026-02-19T15:30:23Z","timestamp":1771515023111,"version":"3.50.1"},"reference-count":26,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2010,5]]},"DOI":"10.1109\/robot.2010.5509336","type":"proceedings-article","created":{"date-parts":[[2010,7,22]],"date-time":"2010-07-22T12:07:20Z","timestamp":1279800440000},"page":"2397-2403","source":"Crossref","is-referenced-by-count":151,"title":["Reinforcement learning of motor skills in high dimensions: A path integral approach"],"prefix":"10.1109","author":[{"given":"Evangelos","family":"Theodorou","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jonas","family":"Buchli","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Stefan","family":"Schaal","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","article-title":"A path integral approach to agent planning","author":"kappen","year":"2007","journal-title":"AAMAS"},{"key":"ref11","doi-asserted-by":"crossref","first-page":"95","DOI":"10.1613\/jair.2473","article-title":"Graphical model inference in optimal control of stochastic multi-agent systems","volume":"32","author":"van den broek","year":"2008","journal-title":"Journal of Artificial Intelligence Research"},{"key":"ref12","first-page":"1547","article-title":"Learning attractor landscapes for learning motor primitives","author":"ijspeert","year":"2003","journal-title":"Advances in Neural Information Processing Systems 15"},{"key":"ref13","author":"sutton","year":"1998","journal-title":"Reinforcement Learning An Introduction Adaptive Computation and Machine Learning"},{"key":"ref14","article-title":"Optimal control and estimation","author":"stengel","year":"1994","journal-title":"Dover Books on Advanced Mathematics"},{"key":"ref15","article-title":"Controlled Markov processes and viscosity solutions","author":"fleming","year":"2006","journal-title":"Applications of Mathematics"},{"key":"ref16","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-642-14394-6_5","article-title":"Stochastic differential equations: an introduction with applications","author":"ksendal","year":"2003","journal-title":"Universitext"},{"key":"ref17","first-page":"2779","article-title":"Relations among odes, pdes, fsdes, bsdes, and fbsdes","volume":"3","author":"yong","year":"1997"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1088\/1742-5468\/2005\/11\/P11011"},{"key":"ref19","first-page":"149","article-title":"An introduction to stochastic control theory, path integrals and reinforcement learning","author":"kappen","year":"2007","journal-title":"Cooperative Behavior in Neural Systems volume 887 of American Institute of Physics Conference Series"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2009.5152577"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.2.271"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143963"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1177\/0278364907087548"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/1273496.1273534"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2008.12.019"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-008-5069-3"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-009-9132-0"},{"key":"ref1","article-title":"Machine learning of motor skills for robotics","author":"peters","year":"2007"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.95.200201"},{"key":"ref22","article-title":"Reinforcement learning for parameterized motor primitives","author":"peters","year":"2006","journal-title":"Proceedings of the 2006 International Joint Conference on Neural Networks (IJCNN 2006)"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2006.282564"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.0710743106"},{"key":"ref23","article-title":"Classic maximum principles and estimation-control dualities for nonlinear stochastic systems","author":"todorov","year":"2009"},{"key":"ref26","article-title":"Stochastic optimal control in continuous space-time multi-agent system","author":"wiegerinck","year":"0","journal-title":"UAI 2006"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.95.200201"}],"event":{"name":"2010 IEEE International Conference on Robotics and Automation (ICRA 2010)","location":"Anchorage, AK","start":{"date-parts":[[2010,5,3]]},"end":{"date-parts":[[2010,5,7]]}},"container-title":["2010 IEEE International Conference on Robotics and Automation"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/5501116\/5509124\/05509336.pdf?arnumber=5509336","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,31]],"date-time":"2019-05-31T08:13:02Z","timestamp":1559290382000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/5509336\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2010,5]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/robot.2010.5509336","relation":{},"subject":[],"published":{"date-parts":[[2010,5]]}}}