{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T13:59:06Z","timestamp":1766066346435,"version":"3.28.0"},"reference-count":16,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2013,11]]},"DOI":"10.1109\/iros.2013.6696506","type":"proceedings-article","created":{"date-parts":[[2014,1,6]],"date-time":"2014-01-06T12:10:53Z","timestamp":1389010253000},"page":"1223-1229","source":"Crossref","is-referenced-by-count":3,"title":["Locally weighted least squares policy iteration for model-free learning in uncertain environments"],"prefix":"10.1109","author":[{"given":"Matthew","family":"Howard","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yoshihiko","family":"Nakamura","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"15","article-title":"Finite-sample analysis of LSTD","author":"lazaric","year":"2010","journal-title":"Int Conf Machine Learning"},{"key":"16","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.1988.10478639"},{"key":"13","doi-asserted-by":"publisher","DOI":"10.1162\/jmlr.2003.4.6.1107"},{"journal-title":"Reinforcement Learning An Introduction","year":"1998","author":"sutton","key":"14"},{"key":"11","doi-asserted-by":"publisher","DOI":"10.1162\/089976600300015961"},{"key":"12","doi-asserted-by":"publisher","DOI":"10.1007\/BF00058926"},{"key":"3","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-642-05181-4_4","article-title":"Adaptive optimal feedback control with learned internal dynamics models","author":"mitrovic","year":"2010","journal-title":"From Motor Learning to Interaction Learning in Robots"},{"journal-title":"Differential Dynamic Programming","year":"1970","author":"jacobson","key":"2"},{"key":"1","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2008.926610"},{"key":"10","doi-asserted-by":"publisher","DOI":"10.1162\/089976698300016963"},{"key":"7","doi-asserted-by":"publisher","DOI":"10.1023\/A:1017936530646"},{"key":"6","article-title":"Locally weighted least squares temporal difference learning","author":"howard","year":"2013","journal-title":"European Symp Artificial Neural Networks"},{"key":"5","first-page":"3137","article-title":"A generalized path integral control approach to reinforcement learning","volume":"11","author":"theodorou","year":"2010","journal-title":"J Machine Learning Research"},{"key":"4","article-title":"Iterative linear-quadratic regulator design for nonlinear biological movement systems","author":"li","year":"2004","journal-title":"Int Conf on Informatics in Control Automation and Robotics"},{"key":"9","doi-asserted-by":"publisher","DOI":"10.1162\/089976605774320557"},{"key":"8","doi-asserted-by":"publisher","DOI":"10.1007\/BF00114723"}],"event":{"name":"2013 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS 2013)","start":{"date-parts":[[2013,11,3]]},"location":"Tokyo","end":{"date-parts":[[2013,11,7]]}},"container-title":["2013 IEEE\/RSJ International Conference on Intelligent Robots and Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6679723\/6696319\/06696506.pdf?arnumber=6696506","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,6,22]],"date-time":"2017-06-22T01:24:27Z","timestamp":1498094667000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/6696506\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,11]]},"references-count":16,"URL":"https:\/\/doi.org\/10.1109\/iros.2013.6696506","relation":{},"subject":[],"published":{"date-parts":[[2013,11]]}}}