{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T04:57:20Z","timestamp":1760245040477,"version":"3.28.0"},"reference-count":13,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2013,10]]},"DOI":"10.1109\/humanoids.2013.7030010","type":"proceedings-article","created":{"date-parts":[[2015,2,10]],"date-time":"2015-02-10T14:57:26Z","timestamp":1423580246000},"page":"429-434","source":"Crossref","is-referenced-by-count":12,"title":["Trajectory-model-based reinforcement learning: Application to bimanual humanoid motor learning with a closed-chain constraint"],"prefix":"10.1109","author":[{"given":"Norikazu","family":"Sugimoto","sequence":"first","affiliation":[]},{"given":"Jun","family":"Morimoto","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","first-page":"1257","article-title":"Sparse Gaussian processes using pseudo-inputs","author":"snelson","year":"2006","journal-title":"Advances in neural information processing systems"},{"key":"ref11","article-title":"The SL simulation and real-time control software package","author":"schaal","year":"2009","journal-title":"Tech Rep"},{"key":"ref12","article-title":"PILCO: A model-based and data-efficient approach to policy search","author":"deisenroth","year":"2011","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2007.4399485"},{"journal-title":"The Computation and Theory of Optimal Control","year":"1970","author":"dyer","key":"ref4"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1162\/089976600300015961"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1088\/1742-5468\/2005\/11\/P11011"},{"journal-title":"Differential Dynamic Programming","year":"1970","author":"jacobson","key":"ref5"},{"key":"ref8","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":"ref7","first-page":"12","article-title":"How Can A Robot Learn from Watching A Human?","author":"atkeson","year":"1997","journal-title":"Proceedings of the Fourteenth International Conference onMachine Learning"},{"key":"ref2","first-page":"1057","article-title":"Policy Gradient Methods for Reinforcement Learning with Function Approximation","author":"sutton","year":"2000","journal-title":"Advances in Neural Information Processing Systems 12"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/nrn3112"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2013.6630740"}],"event":{"name":"2013 13th IEEE-RAS International Conference on Humanoid Robots (Humanoids 2013)","start":{"date-parts":[[2013,10,15]]},"location":"Atlanta, GA","end":{"date-parts":[[2013,10,17]]}},"container-title":["2013 13th IEEE-RAS International Conference on Humanoid Robots (Humanoids)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7016272\/7029946\/07030010.pdf?arnumber=7030010","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,3,24]],"date-time":"2017-03-24T01:39:05Z","timestamp":1490319545000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7030010\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,10]]},"references-count":13,"URL":"https:\/\/doi.org\/10.1109\/humanoids.2013.7030010","relation":{},"subject":[],"published":{"date-parts":[[2013,10]]}}}