{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,10]],"date-time":"2025-06-10T22:02:44Z","timestamp":1749592964028,"version":"3.28.0"},"reference-count":12,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2013,5]]},"DOI":"10.1109\/icra.2013.6630740","type":"proceedings-article","created":{"date-parts":[[2013,10,21]],"date-time":"2013-10-21T22:11:25Z","timestamp":1382393485000},"page":"1311-1316","source":"Crossref","is-referenced-by-count":2,"title":["Off-line path integral reinforcement learning using stochastic robot dynamics approximated by sparse pseudo-input Gaussian processes: Application to humanoid robot motor learning in the real environment"],"prefix":"10.1109","author":[{"given":"Norikazu","family":"Sugimoto","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jun","family":"Morimoto","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"3","doi-asserted-by":"publisher","DOI":"10.1162\/089976600300015961"},{"key":"2","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":"10","first-page":"1257","article-title":"Sparse Gaussian processes using pseudo-inputs","author":"snelson","year":"2006","journal-title":"Advances in neural information processing systems"},{"key":"1","doi-asserted-by":"publisher","DOI":"10.1163\/156855308X324785"},{"key":"7","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 on Machine Learning"},{"key":"6","doi-asserted-by":"publisher","DOI":"10.1088\/1742-5468\/2005\/11\/P11011"},{"journal-title":"Differential Dynamic Programming","year":"1970","author":"jacobson","key":"5"},{"journal-title":"The Computation and Theory of Optimal Control","year":"1970","author":"dyer","key":"4"},{"key":"9","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-009-9133-z"},{"key":"8","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"},{"journal-title":"The SL simulation and real-time control software package","year":"2009","author":"schaal","key":"11"},{"key":"12","doi-asserted-by":"publisher","DOI":"10.1163\/156855307781389356"}],"event":{"name":"2013 IEEE International Conference on Robotics and Automation (ICRA)","start":{"date-parts":[[2013,5,6]]},"location":"Karlsruhe, Germany","end":{"date-parts":[[2013,5,10]]}},"container-title":["2013 IEEE International Conference on Robotics and Automation"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6615630\/6630547\/06630740.pdf?arnumber=6630740","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,3,22]],"date-time":"2017-03-22T22:37:30Z","timestamp":1490222250000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/6630740\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,5]]},"references-count":12,"URL":"https:\/\/doi.org\/10.1109\/icra.2013.6630740","relation":{},"subject":[],"published":{"date-parts":[[2013,5]]}}}