{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T18:11:58Z","timestamp":1730225518741,"version":"3.28.0"},"reference-count":25,"publisher":"IEEE","license":[{"start":{"date-parts":[[2014,11,1]],"date-time":"2014-11-01T00:00:00Z","timestamp":1414800000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2014,11,1]],"date-time":"2014-11-01T00:00:00Z","timestamp":1414800000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2014,11]]},"DOI":"10.1109\/humanoids.2014.7041414","type":"proceedings-article","created":{"date-parts":[[2015,2,18]],"date-time":"2015-02-18T00:28:49Z","timestamp":1424219329000},"page":"535-540","source":"Crossref","is-referenced-by-count":3,"title":["ROCK* \u2014 Efficient black-box optimization for policy learning"],"prefix":"10.1109","author":[{"given":"Jemin","family":"Hwangbo","sequence":"first","affiliation":[{"name":"The initial research to this study has been done while the first author was at the Agile & Dexterous Robotics Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Christian","family":"Gehring","sequence":"additional","affiliation":[{"name":"Autonomous Systems Lab (ASL), ETH Zurich, Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hannes","family":"Sommer","sequence":"additional","affiliation":[{"name":"Autonomous Systems Lab (ASL), ETH Zurich, Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Roland","family":"Siegwart","sequence":"additional","affiliation":[{"name":"Autonomous Systems Lab (ASL), ETH Zurich, Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jonas","family":"Buchli","sequence":"additional","affiliation":[{"name":"Agile & Dexterous Robotics Lab (ADRL), ETH Zurich, Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2014.6907476"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1117\/12.919939"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177729392"},{"key":"ref13","article-title":"An overview of the simultaneous perturbation method for efficient optimization","volume":"19","author":"spall","year":"1998","journal-title":"Johns Hopkins APL Technical Digest"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1162\/NECO_a_00452"},{"key":"ref15","first-page":"5","article-title":"Simple statistical gradient-following algorithms for con-nectionist reinforcement learning","volume":"173","author":"williams","year":"1992","journal-title":"Reinforcement Learning ser The Springer International Series in Engineering and Computer Science"},{"key":"ref16","article-title":"On using simultaneous perturbation stochastic approximation for ir measures, and the empirical optimality of lamb-darank","author":"yue","year":"2007","journal-title":"Advances in neural information processing systems"},{"key":"ref17","doi-asserted-by":"crossref","first-page":"133","DOI":"10.1007\/978-3-540-87700-4_14","article-title":"Parallel Problem Solving from Nature","volume":"5199","author":"bosman","year":"2008","journal-title":"ser Lecture Notes in Computer Science"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4757-4321-0"},{"key":"ref19","article-title":"Gaussian process bandits without regret: An experimental design approach","volume":"abs 912 3995","author":"srinivas","year":"2009","journal-title":"CoRR"},{"key":"ref4","article-title":"Path integral policy improvement with covariance matrix adaptation","author":"stulp","year":"2012","journal-title":"CoRR"},{"key":"ref3","first-page":"3137","article-title":"A generalized path integral control approach to reinforcement learning","volume":"11","author":"theodorou","year":"2010","journal-title":"J Mach Learn Res"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1177\/0278364911402527"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2007.11.026"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.2478\/pjbr-2013-0003"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2013.6696352"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1162\/106365601750190398"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913495721"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1998.675489"},{"key":"ref22","first-page":"1523","article-title":"Learning attractor landscapes for learning motor primitives","volume":"15","author":"ijspeert","year":"2002","journal-title":"Advances in neural information processing systems"},{"year":"0","key":"ref21"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1177\/0959651811402275"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2011.6094504"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1142\/9789814415958_0062"}],"event":{"name":"2014 IEEE-RAS 14th International Conference on Humanoid Robots (Humanoids 2014)","start":{"date-parts":[[2014,11,18]]},"location":"Madrid, Spain","end":{"date-parts":[[2014,11,20]]}},"container-title":["2014 IEEE-RAS International Conference on Humanoid Robots"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7028729\/7041308\/07041414.pdf?arnumber=7041414","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,2]],"date-time":"2023-01-02T19:16:54Z","timestamp":1672687014000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/7041414\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014,11]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/humanoids.2014.7041414","relation":{},"subject":[],"published":{"date-parts":[[2014,11]]}}}