{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T10:01:39Z","timestamp":1772791299623,"version":"3.50.1"},"reference-count":14,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2010,12]]},"DOI":"10.1109\/ichr.2010.5686320","type":"proceedings-article","created":{"date-parts":[[2011,1,13]],"date-time":"2011-01-13T21:34:20Z","timestamp":1294954460000},"page":"405-410","source":"Crossref","is-referenced-by-count":38,"title":["Reinforcement learning of full-body humanoid motor skills"],"prefix":"10.1109","author":[{"given":"Freek","family":"Stulp","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jonas","family":"Buchli","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Evangelos","family":"Theodorou","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","author":"stengel","year":"1994","journal-title":"Optimal Control and Estimation"},{"key":"ref11","author":"sutton","year":"1998","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref12","article-title":"Reinforcement learning in high dimensional state spaces: A path integral approach","author":"theodorou","year":"2010","journal-title":"Journal of Machine Learning Research"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553508"},{"key":"ref14","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","year":"2008","journal-title":"Journal of Artificial Intelligence Research"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2002.1014739"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1115\/1.3140702"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1023\/A:1013219111657"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2009.5152577"},{"key":"ref8","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4471-0449-0","author":"sciavicco","year":"2000","journal-title":"Modelling and Control of Robot Manipulators"},{"key":"ref7","article-title":"The SL simulation and real-time control software package","author":"schaal","year":"2009","journal-title":"Technical Report"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1163\/156855307781389356"},{"key":"ref1","article-title":"Variable impedance control - a reinforcement learning approach","author":"buchli","year":"2010","journal-title":"Robotics Science and Systems Conference (RSS)"},{"key":"ref9","author":"sentis","year":"2007","journal-title":"Synthesis and control of whole-body behaviors in humanoid systems"}],"event":{"name":"2010 10th IEEE-RAS International Conference on Humanoid Robots (Humanoids 2010)","location":"Nashville, TN, USA","start":{"date-parts":[[2010,12,6]]},"end":{"date-parts":[[2010,12,8]]}},"container-title":["2010 10th IEEE-RAS International Conference on Humanoid Robots"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/5679985\/5686265\/05686320.pdf?arnumber=5686320","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,6,7]],"date-time":"2019-06-07T20:46:30Z","timestamp":1559940390000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/5686320\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2010,12]]},"references-count":14,"URL":"https:\/\/doi.org\/10.1109\/ichr.2010.5686320","relation":{},"subject":[],"published":{"date-parts":[[2010,12]]}}}