{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,23]],"date-time":"2024-10-23T03:36:45Z","timestamp":1729654605760,"version":"3.28.0"},"reference-count":14,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2011,12]]},"DOI":"10.1109\/cdc.2011.6161518","type":"proceedings-article","created":{"date-parts":[[2012,3,7]],"date-time":"2012-03-07T21:18:31Z","timestamp":1331155111000},"page":"2856-2862","source":"Crossref","is-referenced-by-count":4,"title":["PRISCA: A policy search method for extreme trajectory following"],"prefix":"10.1109","author":[{"given":"Tak Kit","family":"Lau","sequence":"first","affiliation":[]}],"member":"263","reference":[{"key":"13","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4757-6015-6","author":"shor","year":"1998","journal-title":"Nondifferentiable Optimization and Polynomial Problems"},{"key":"14","article-title":"PEGASUS: A policy search method for large MDPs and POMDPs","author":"ng","year":"2000","journal-title":"Proceedings of the 16th Conference on Uncertainty in Artificial Intelligence"},{"doi-asserted-by":"publisher","key":"11","DOI":"10.1145\/1015330.1015430"},{"doi-asserted-by":"publisher","key":"12","DOI":"10.1109\/ROBOT.2010.5509562"},{"key":"3","article-title":"Policy search for motor primitives in robotics","volume":"22","author":"kober","year":"2009","journal-title":"Advances in neural information processing systems"},{"doi-asserted-by":"publisher","key":"2","DOI":"10.1145\/1273496.1273590"},{"key":"1","doi-asserted-by":"crossref","DOI":"10.15607\/RSS.2009.V.027","article-title":"Policy search via the signed derivative","author":"kolter","year":"2009","journal-title":"Proceedings of Robotics Science and Systems"},{"doi-asserted-by":"publisher","key":"10","DOI":"10.1145\/1390156.1390175"},{"key":"7","article-title":"Stable adaptive control with online learning","author":"ng","year":"2004","journal-title":"Advances in neural information processing systems"},{"key":"6","article-title":"Variance reduction techniques for gradient estimates in reinforcement learning","volume":"5","author":"greensmith","year":"2004","journal-title":"The Journal of Machine Learning Research"},{"key":"5","article-title":"On a connection between importance sampling and the likelihood ratio policy gradient","author":"tang","year":"2010","journal-title":"Advances in neural information processing systems"},{"doi-asserted-by":"publisher","key":"4","DOI":"10.1145\/84537.84552"},{"key":"9","first-page":"12","article-title":"Robot learning from demonstration","author":"atkeson","year":"1997","journal-title":"Proceedings of the Fourteenth International Conference on Machine Learning"},{"doi-asserted-by":"publisher","key":"8","DOI":"10.1109\/ROBOT.1997.614389"}],"event":{"name":"2011 50th IEEE Conference on Decision and Control and European Control Conference (CDC-ECC 2011)","start":{"date-parts":[[2011,12,12]]},"location":"Orlando, FL, USA","end":{"date-parts":[[2011,12,15]]}},"container-title":["IEEE Conference on Decision and Control and European Control Conference"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/6149620\/6159299\/06161518.pdf?arnumber=6161518","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,6,25]],"date-time":"2019-06-25T01:56:35Z","timestamp":1561427795000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/6161518\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2011,12]]},"references-count":14,"URL":"https:\/\/doi.org\/10.1109\/cdc.2011.6161518","relation":{},"subject":[],"published":{"date-parts":[[2011,12]]}}}