{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T04:57:19Z","timestamp":1760245039374,"version":"3.28.0"},"reference-count":29,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2014,5]]},"DOI":"10.1109\/icra.2014.6907631","type":"proceedings-article","created":{"date-parts":[[2014,9,30]],"date-time":"2014-09-30T20:32:36Z","timestamp":1412109156000},"page":"5252-5259","source":"Crossref","is-referenced-by-count":8,"title":["Combining learned controllers to achieve new goals based on linearly solvable MDPs"],"prefix":"10.1109","author":[{"given":"Eiji","family":"Uchibe","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kenji","family":"Doya","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Aggregation Methods for Lineary-solvable Markov Decision Process","author":"zhong","year":"2011","journal-title":"Proc of the World Congress of the International Federation of Automatic Control"},{"key":"ref11","first-page":"1856","article-title":"Compositionality of optimal control laws","author":"todorov","year":"2009","journal-title":"Advances in Neural Information Processing Systems 22"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/1531326.1531388"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.3389\/fnbot.2013.00007"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1023\/A:1017936530646"},{"key":"ref15","first-page":"1107","article-title":"Least-Squares Policy Iteration","volume":"4","author":"lagoudakis","year":"2003","journal-title":"Journal of Machine Learning Research"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1162\/089976602753712972"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/DevLrn.2012.6400845"},{"journal-title":"Controlled Markov Processes and Viscosity Solutions","year":"2006","author":"fleming","key":"ref18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/s10339-011-0404-1"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/DevLrn.2013.6652533"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuron.2011.02.027"},{"key":"ref27","article-title":"Phase-dependent trajectory optimization for periodic movement using path integral reinforcement learning","author":"sugimoto","year":"2011","journal-title":"Proc of Annual Conference of Japanese Neural Network Society"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.jmp.2008.12.005"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.0710743106"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.orl.2011.06.014"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.conb.2012.08.003"},{"key":"ref8","first-page":"1369","article-title":"Linearly-solvable Markov decision problems","author":"todorov","year":"2007","journal-title":"Advances in Neural Information Processing Systems 19"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.0905423106"},{"journal-title":"Reinforcement Learning","year":"1998","author":"sutton","key":"ref2"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ADPRL.2009.4927540"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/9780262042383.003.0012"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2011.07.006"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2012.6426381"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2008.4543306"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1088\/1742-5468\/2005\/11\/P11011"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.95.200201"},{"key":"ref26","article-title":"Path Integral Policy Improvement with Covariance Matrix Adaptation","author":"stulp","year":"2012","journal-title":"Proc of the 10th European Workshop on Reinforcement Learning (EWRL 2012)"},{"key":"ref25","first-page":"3137","article-title":"A Generalized Path Integral Control Approach to Reinforcement Learning","volume":"11","author":"theodorou","year":"2010","journal-title":"Journal of Machine Learning Research"}],"event":{"name":"2014 IEEE International Conference on Robotics and Automation (ICRA)","start":{"date-parts":[[2014,5,31]]},"location":"Hong Kong, China","end":{"date-parts":[[2014,6,7]]}},"container-title":["2014 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6895053\/6906581\/06907631.pdf?arnumber=6907631","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,3,23]],"date-time":"2017-03-23T21:26:04Z","timestamp":1490304364000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/6907631\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014,5]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/icra.2014.6907631","relation":{},"subject":[],"published":{"date-parts":[[2014,5]]}}}