{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T08:02:56Z","timestamp":1758268976719,"version":"3.28.0"},"reference-count":30,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019,1]]},"DOI":"10.1109\/ccwc.2019.8666449","type":"proceedings-article","created":{"date-parts":[[2019,3,18]],"date-time":"2019-03-18T23:58:55Z","timestamp":1552953535000},"page":"0240-0246","source":"Crossref","is-referenced-by-count":2,"title":["Bayesian Learning for Policy Search in Trajectory Control of a Planar Manipulator"],"prefix":"10.1109","author":[{"given":"Vahid Tavakol","family":"Aghaei","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Arda","family":"Agababaoglu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ahmet","family":"Onat","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sinan","family":"Yildirim","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-006-0235-1"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1049\/ip-f-2.1993.0015"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/78.984776"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4757-3437-9_9"},{"key":"ref13","first-page":"849","article-title":"Policy search for motor primitives in robotics","volume":"21","author":"kober","year":"2009","journal-title":"Advances in neural information processing systems"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1002\/oca.789"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1287\/mnsc.18.7.356"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1023\/A:1017940631555"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1162\/NECO_a_00600"},{"key":"ref19","article-title":"Particle value functions","author":"maddison","year":"2017","journal-title":"ICLR 2017 Workshop track"},{"key":"ref28","doi-asserted-by":"crossref","DOI":"10.1002\/9780470117811","author":"ravindran","year":"2006","journal-title":"Engineering Optimization Methods and Applications"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.csda.2010.10.004"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1111\/rssb.12280"},{"key":"ref3","article-title":"Reinforcement learning for continuous action using stochastic gradient ascent","author":"kimura","year":"1988","journal-title":"International Conference on Intelligent Autonomous Systems"},{"key":"ref6","doi-asserted-by":"crossref","DOI":"10.1109\/IROS.2006.282564","article-title":"Policy gradient methods for robotics","author":"peters","year":"2006","journal-title":"Proceedings of the IEEE\/RSJ International Conference on Intelligent Robots and Systems"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/S1006-1266(07)60009-1"},{"key":"ref5","first-page":"2011","article-title":"An approximate inference approach to temporal optimization in optimal control","author":"rawlik","year":"2010","journal-title":"Advances in Neural Information Processing Systems 23"},{"key":"ref8","first-page":"262","article-title":"Analysis and improvement of policy gradient estimation","author":"zhao","year":"2011","journal-title":"Advances in Neural Information Processing Systems 24"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2005.1545206"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"13","DOI":"10.1109\/37.257890","article-title":"Acquiring robot skills via reinforcement learning","volume":"14","author":"gullapalli","year":"1994","journal-title":"IEEE Control Systems"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1080\/21642583.2018.1528483"},{"journal-title":"Reinforcement Learning An Introduction","year":"1998","author":"sutton","key":"ref1"},{"key":"ref20","first-page":"665","article-title":"Bayesian policy learning with trans-dimensional MCMC","author":"hoffman","year":"2008","journal-title":"In Advances in Neural Information Processing Systems 20"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1023\/A:1020281327116"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1093\/biomet\/82.4.711"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4684-9393-1"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/5992.814660"},{"key":"ref26","article-title":"Efficient implementation of Markov chain Monte Carlo when using an unbiased likelihood estimator","author":"doucet","year":"2012","journal-title":"Biometrika"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1214\/07-AOS574"}],"event":{"name":"2019 IEEE 9th Annual Computing and Communication Workshop and Conference (CCWC)","start":{"date-parts":[[2019,1,7]]},"location":"Las Vegas, NV, USA","end":{"date-parts":[[2019,1,9]]}},"container-title":["2019 IEEE 9th Annual Computing and Communication Workshop and Conference (CCWC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8663971\/8666184\/08666449.pdf?arnumber=8666449","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,14]],"date-time":"2023-09-14T16:49:52Z","timestamp":1694710192000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8666449\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,1]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/ccwc.2019.8666449","relation":{},"subject":[],"published":{"date-parts":[[2019,1]]}}}