{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T22:20:36Z","timestamp":1775341236381,"version":"3.50.1"},"reference-count":34,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017,5]]},"DOI":"10.1109\/icra.2017.7989384","type":"proceedings-article","created":{"date-parts":[[2017,7,25]],"date-time":"2017-07-25T17:44:28Z","timestamp":1501004668000},"page":"3381-3388","source":"Crossref","is-referenced-by-count":74,"title":["Path integral guided policy search"],"prefix":"10.1109","author":[{"given":"Yevgen","family":"Chebotar","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mrinal","family":"Kalakrishnan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ali","family":"Yahya","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Adrian","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Stefan","family":"Schaal","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sergey","family":"Levine","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","article-title":"Joint training of a convolutional network and a graphical model for human pose estimation","author":"tompson","year":"0","journal-title":"NIPS 2014"},{"key":"ref32","article-title":"Path integral policy improvement with covariance matrix adaptation","author":"stulp","year":"0","journal-title":"ICML 2012"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/2576768.2598358"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2014.09.003"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_51"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2014.6943031"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2010.VI.005"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2016.7759309"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1177\/0278364907084980"},{"key":"ref14","first-page":"1","article-title":"A survey on policy search for robotics","author":"deisenroth","year":"2013","journal-title":"Foundations and Trends in Robotics"},{"key":"ref15","article-title":"Trust region policy optimization","author":"schulman","year":"0","journal-title":"ICML 2015"},{"key":"ref16","article-title":"Guided policy search","author":"levine","year":"0","journal-title":"ICML 2013"},{"key":"ref17","article-title":"Learning neural network policies with guided policy search under unknown dynamics","author":"levine","year":"0","journal-title":"NIPS 2014"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7138994"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2002.1014739"},{"key":"ref28","article-title":"Learning of non-parametric control policies with high-dimensional state features","author":"van hoof","year":"2015","journal-title":"AISTATS"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2011.VII.008"},{"key":"ref27","year":"0","journal-title":"ECM\/PKDD 2014"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2008.4650953"},{"key":"ref6","article-title":"End-to-end training of deep visuomotor policies","author":"levine","year":"2016","journal-title":"JMLR"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/BF00344251"},{"key":"ref5","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"0","journal-title":"ICLR 2016"},{"key":"ref8","article-title":"Guided policy search as approximate mirror descent","author":"montgomery","year":"2016","journal-title":"CoRR"},{"key":"ref7","article-title":"A generalized path integral control approach to reinforcement learning","author":"theodorou","year":"2010","journal-title":"JMLR"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2004.1307456"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2009.5152385"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2004.1389841"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2011.5979644"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TAMD.2012.2205924"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2012.2210294"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2016.XII.033"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2011.6095096"},{"key":"ref26","article-title":"Sample-based information-theoretic stochastic optimal control. I","author":"lioutikov","year":"0","journal-title":"ICRA 2014"},{"key":"ref25","article-title":"Relative entropy policy search","author":"peters","year":"0","journal-title":"AAAI' 2010"}],"event":{"name":"2017 IEEE International Conference on Robotics and Automation (ICRA)","location":"Singapore, Singapore","start":{"date-parts":[[2017,5,29]]},"end":{"date-parts":[[2017,6,3]]}},"container-title":["2017 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7960754\/7988677\/07989384.pdf?arnumber=7989384","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,8,16]],"date-time":"2017-08-16T11:36:26Z","timestamp":1502883386000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7989384\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,5]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/icra.2017.7989384","relation":{},"subject":[],"published":{"date-parts":[[2017,5]]}}}