{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,23]],"date-time":"2024-10-23T06:06:35Z","timestamp":1729663595654,"version":"3.28.0"},"reference-count":24,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2015,11]]},"DOI":"10.1109\/humanoids.2015.7363503","type":"proceedings-article","created":{"date-parts":[[2015,12,28]],"date-time":"2015-12-28T16:34:48Z","timestamp":1451320488000},"page":"1083-1089","source":"Crossref","is-referenced-by-count":5,"title":["Local Update Dynamic Policy Programming in reinforcement learning of pneumatic artificial muscle-driven humanoid hand control"],"prefix":"10.1109","author":[{"given":"Yunduan","family":"Cui","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Takamitsu","family":"Matsubara","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kenji","family":"Sugimoto","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2010.5649089"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref12","first-page":"1038","article-title":"Generalization in reinforcement learning: Successful examples using sparse coarse coding","author":"sutton","year":"1996","journal-title":"Advances in neural information processing systems"},{"key":"ref13","doi-asserted-by":"crossref","first-page":"319","DOI":"10.1613\/jair.806","article-title":"Infinite-horizon policy-gradient estimation","volume":"12","author":"baxter","year":"2001","journal-title":"Journal of Artificial Intelligence Research"},{"key":"ref14","first-page":"119","article-title":"Dynamic policy programming with function approximation","author":"azar","year":"2011","journal-title":"International Conference on Artificial Intelligence and Statistics"},{"key":"ref15","first-page":"3207","article-title":"Dynamic policy programming","volume":"13","author":"azar","year":"2012","journal-title":"The Journal of Machine Learning Research"},{"key":"ref16","first-page":"1107","article-title":"Least-squares policy iteration","volume":"4","author":"lagoudakis","year":"2003","journal-title":"The Journal of Machine Learning Research"},{"key":"ref17","first-page":"583","article-title":"Latent Kullback Leibler control for continuous-state systems using probabilistic graphical models","author":"matsubara","year":"2014","journal-title":"Conference on Uncertainty in Artificial Intelligence"},{"key":"ref18","article-title":"Shadow dextrous hand technical specification","author":"walker","year":"2013","journal-title":"Shadow Robot Company"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1023\/A:1006559212014"},{"journal-title":"Reinforcement Learning An Introduction","year":"1998","author":"sutton","key":"ref4"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6385778"},{"key":"ref6","first-page":"1607","article-title":"Relative entropy policy search","author":"peters","year":"2010","journal-title":"Association for the Advancement of Artificial Intelligence (AAAI'05)"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2007.11.026"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913495721"},{"key":"ref7","first-page":"3137","article-title":"A generalized path integral control approach to reinforcement learning","volume":"11","author":"theodorou","year":"2010","journal-title":"The Journal of Machine Learning Research"},{"key":"ref2","first-page":"11","article-title":"Pneumatic artificial muscles: actuators for robotics and automation","volume":"47","author":"daerden","year":"2002","journal-title":"European Journal of Mechanical and Environmental Engineering"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/70.481753"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1177\/0278364907084980"},{"key":"ref20","first-page":"1225","article-title":"Fast Gaussian process regression using KD-trees","author":"shen","year":"2006","journal-title":"Proc 19th Annu Conf Neural Informat Process Syst"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/361002.361007"},{"journal-title":"Nearest Neighbor Search The Old the New and the Impossible","year":"2009","author":"andoni","key":"ref21"},{"key":"ref24","first-page":"733","article-title":"Online exploration in least-squares policy iteration","author":"li","year":"2009","journal-title":"the 8th International Conference on Autonomous Agents and Multiagent Systems-Volume 2"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.2010.5530856"}],"event":{"name":"2015 IEEE-RAS 15th International Conference on Humanoid Robots (Humanoids)","start":{"date-parts":[[2015,11,3]]},"location":"Seoul, South Korea","end":{"date-parts":[[2015,11,5]]}},"container-title":["2015 IEEE-RAS 15th International Conference on Humanoid Robots (Humanoids)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7349033\/7362951\/07363503.pdf?arnumber=7363503","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,9,2]],"date-time":"2019-09-02T20:34:32Z","timestamp":1567456472000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7363503\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,11]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/humanoids.2015.7363503","relation":{},"subject":[],"published":{"date-parts":[[2015,11]]}}}