{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2022,7,3]],"date-time":"2022-07-03T00:49:06Z","timestamp":1656809346667},"reference-count":36,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2016,3,1]],"date-time":"2016-03-01T00:00:00Z","timestamp":1456790400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Automat. Mag."],"published-print":{"date-parts":[[2016,3]]},"DOI":"10.1109\/mra.2015.2511681","type":"journal-article","created":{"date-parts":[[2016,2,24]],"date-time":"2016-02-24T22:36:43Z","timestamp":1456353403000},"page":"96-105","source":"Crossref","is-referenced-by-count":6,"title":["Trial and Error: Using Previous Experiences as Simulation Models in Humanoid Motor Learning"],"prefix":"10.1109","volume":"23","author":[{"given":"Norikazu","family":"Sugimoto","sequence":"first","affiliation":[]},{"given":"Voot","family":"Tangkaratt","sequence":"additional","affiliation":[]},{"given":"Thijs","family":"Wensveen","sequence":"additional","affiliation":[]},{"given":"Tingting","family":"Zhao","sequence":"additional","affiliation":[]},{"given":"Masashi","family":"Sugiyama","sequence":"additional","affiliation":[]},{"given":"Jun","family":"Morimoto","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2011.09.005"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2006.05.012"},{"key":"ref31","article-title":"The SL simulation and real-time control software package","author":"schaal","year":"2009","journal-title":"Tech Rep"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1162\/089976698300016963"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/MRA.2010.936957"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2014.06.006"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1162\/NECO_a_00452"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2006.282564"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/1273496.1273590"},{"key":"ref12","first-page":"1607","article-title":"Relative Entropy Policy Search","author":"peters","year":"0","journal-title":"Proc 24th AAAI Conf Artificial Intelligence"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1989.1.2.281"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-009-9133-z"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2007.11.026"},{"key":"ref16","first-page":"538","article-title":"The optimal reward baseline for gradient-based reinforcement learning","author":"weaver","year":"0","journal-title":"Proc 7th Conf Uncertainty Artificial Intelligence"},{"key":"ref17","first-page":"465","article-title":"PILCO: A model-based and data efficient approach to policy search","author":"deisenroth","year":"0","journal-title":"Proc Int Conf Machine Learning"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.218"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/Humanoids.2011.6100908"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2009.191"},{"key":"ref4","first-page":"1643","article-title":"Nonparametric representation of policies and value functions: A trajectory-based approach","author":"atkeson","year":"0","journal-title":"Proc Neural Information Processing Systems"},{"key":"ref27","author":"sutton","year":"1998","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref3","first-page":"12","article-title":"Robot learning from demonstration","author":"atkeson","year":"0","journal-title":"Proc 14th Int Conf Machine Learning"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2009.12.004"},{"key":"ref29","first-page":"1531","article-title":"A natural policy gradient","volume":"14","author":"kakade","year":"0","journal-title":"Proc Advances Neural Information Processing Systems"},{"key":"ref5","first-page":"1471","article-title":"Variance reduction techniques for gradient estimates in reinforcement learning","volume":"5","author":"greensmith","year":"2004","journal-title":"J Machine Learning Res"},{"key":"ref8","author":"fishman","year":"1996","journal-title":"Monte Carlo Concepts Algorithms and Applications"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1163\/156855307781389356"},{"key":"ref2","author":"rasmussen","year":"2006","journal-title":"Williams Gaussian Processes for Machine Learning"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1162\/NECO_a_00199"},{"key":"ref1","article-title":"Data-efficient contextual policy search for robot movement skills","author":"kupcsik","year":"0","journal-title":"Proc National Conf Artificial Intelligence"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1162\/NECO_a_00246"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/HUMANOIDS.2013.7030010"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2012.01.002"},{"key":"ref24","article-title":"Toward a theory of reinforcement-learning connectionist systems","author":"williams","year":"1988","journal-title":"Tech Rep NU-CCS-88-3"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/HUMANOIDS.2014.7041417"},{"key":"ref26","author":"sutton","year":"1984","journal-title":"Temporal credit assignment in reinforcement learning"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"}],"container-title":["IEEE Robotics & Automation Magazine"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/100\/7426477\/7419233.pdf?arnumber=7419233","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T16:48:15Z","timestamp":1642006095000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7419233\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,3]]},"references-count":36,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/mra.2015.2511681","relation":{},"ISSN":["1070-9932"],"issn-type":[{"value":"1070-9932","type":"print"}],"subject":[],"published":{"date-parts":[[2016,3]]}}}