{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T06:46:36Z","timestamp":1730270796298,"version":"3.28.0"},"reference-count":26,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2007,10]]},"DOI":"10.1109\/iros.2007.4399449","type":"proceedings-article","created":{"date-parts":[[2008,1,9]],"date-time":"2008-01-09T14:23:35Z","timestamp":1199888615000},"page":"1022-1027","source":"Crossref","is-referenced-by-count":9,"title":["Using reinforcement learning to adapt an imitation task"],"prefix":"10.1109","author":[{"given":"Florent","family":"Guenter","sequence":"first","affiliation":[]},{"given":"Aude G.","family":"Billard","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/S0921-8890(01)00113-0"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2004.1389902"},{"key":"ref12","article-title":"Reinforcement learning methods for continuous-time markov decision problems","author":"bratke","year":"1994","journal-title":"Neural Information Processing Systems Conference"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1162\/089976600300015961"},{"journal-title":"Reinforcement Learning An Introduction","year":"1998","author":"sutton","key":"ref14"},{"key":"ref15","article-title":"Actor-critic algorithms","author":"konda","year":"2000","journal-title":"Advances in Neural Information Processing Systems 12"},{"key":"ref16","article-title":"Least-squares policy evaluation algorithms with linear function approximation","author":"nedic","year":"2001","journal-title":"Discrete Event Systems"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"ref18","article-title":"Policy gradient methods for reinforcement learning with function approximation","author":"sutton","year":"2000","journal-title":"Advances in Neural Information Processing Systems 12"},{"key":"ref19","first-page":"343","article-title":"Recent advances in hierarchical reinforcement learning","volume":"13","author":"barto","year":"2003","journal-title":"Discrete Event Dynamic Systems Theory and Applications"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/0921-8890(95)00049-6"},{"key":"ref3","article-title":"Learning dynamical system modulation for constraint reaching tasks","author":"hersch","year":"2006","journal-title":"IEEE-RAS International Conference on Humanoid Robots HUMANOIDS"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2004.1302393"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/BIOROB.2006.1639233"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.1997.614389"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2006.1641933"},{"key":"ref2","volume":"47","author":"billard","year":"2004","journal-title":"Robotics and Autonomous Systems Special Issue Robot Learning from Demonstration"},{"key":"ref9","article-title":"Learning movement primitives","author":"schaal","year":"2004","journal-title":"International Symposium on Robotics Research (ISRR2003) Springer Tracts in Advanced Robotics"},{"journal-title":"Imitation in Animals and Artifacts","year":"2001","author":"dautenhahn","key":"ref1"},{"key":"ref20","article-title":"Reinforcement learning for humanoid robotics","author":"peters","year":"2003","journal-title":"Humanoids2003 Third IEEE-RAS International Conference on Humanoid Robots"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1162\/089976698300017746"},{"key":"ref21","first-page":"280","article-title":"Natural actor-critic","author":"peters","year":"2005","journal-title":"16th European Conference on Machine Learning"},{"key":"ref24","article-title":"Supervised learning from incomplete data via an em approach","volume":"6","author":"ghahramani","year":"1994","journal-title":"Advances in neural information processing systems"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2006.886952"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1023\/A:1017936530646"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2006.01.007"}],"event":{"name":"2007 IEEE\/RSJ International Conference on Intelligent Robots and Systems","start":{"date-parts":[[2007,10,29]]},"location":"San Diego, CA, USA","end":{"date-parts":[[2007,11,2]]}},"container-title":["2007 IEEE\/RSJ International Conference on Intelligent Robots and Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/4398943\/4398944\/04399449.pdf?arnumber=4399449","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,3,16]],"date-time":"2017-03-16T11:38:39Z","timestamp":1489664319000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/4399449\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2007,10]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/iros.2007.4399449","relation":{},"subject":[],"published":{"date-parts":[[2007,10]]}}}