{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T22:12:25Z","timestamp":1740175945214,"version":"3.37.3"},"reference-count":27,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2018,10,1]],"date-time":"2018-10-01T00:00:00Z","timestamp":1538352000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"DOI":"10.13039\/100006732","name":"New York University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006732","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Max-Planck Society"},{"name":"Max Planck ETH center for learning systems"},{"name":"European Union's Horizon 2020 research and innovation programme","award":["780684"],"award-info":[{"award-number":["780684"]}]},{"name":"European Research Council's","award":["637935"],"award-info":[{"award-number":["637935"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2018,10]]},"DOI":"10.1109\/lra.2018.2861466","type":"journal-article","created":{"date-parts":[[2018,7,31]],"date-time":"2018-07-31T21:03:52Z","timestamp":1533071032000},"page":"4092-4099","source":"Crossref","is-referenced-by-count":7,"title":["Learning a Structured Neural Network Policy for a Hopping Task"],"prefix":"10.1109","volume":"3","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9049-5873","authenticated-orcid":false,"given":"Julian","family":"Viereck","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jules","family":"Kozolinsky","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7671-1878","authenticated-orcid":false,"given":"Alexander","family":"Herzog","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6458-9112","authenticated-orcid":false,"given":"Ludovic","family":"Righetti","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","first-page":"1","article-title":"Guided policy search","volume":"3","author":"levine","year":"0","journal-title":"Proc 30th Int Conf Mach Learn"},{"key":"ref11","first-page":"222","article-title":"Iterative linear quadratic regulator design for nonlinear biological movement systems","author":"li","year":"0","journal-title":"Proc Int Conf Inform Control Autom Robot"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref13","doi-asserted-by":"crossref","first-page":"484","DOI":"10.1038\/nature16961","article-title":"Mastering the game of go with deep neural\n networks and tree search","volume":"529","author":"silver","year":"2016","journal-title":"Nature"},{"key":"ref14","doi-asserted-by":"crossref","first-page":"354","DOI":"10.1038\/nature24270","article-title":"Mastering the game of go without human\n knowledge","volume":"550","author":"silver","year":"2017","journal-title":"Nature"},{"article-title":"Emergence of locomotion behaviours in rich\n environments","year":"2017","author":"heess","key":"ref15"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/37.257895"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7138994"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487143"},{"journal-title":"Pattern Recognition and Machine Learning (Information Science and Statistics)","year":"2006","author":"bishop","key":"ref19"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487664"},{"article-title":"Openai baselines","year":"2017","author":"dhariwal","key":"ref27"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2016.7759420"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2015.7353843"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/HUMANOIDS.2013.7029990"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487270"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2800124"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2014.6907001"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2014.X.052"},{"key":"ref1","first-page":"527","article-title":"Direct trajectory optimization of rigid body dynamical systems through contact","author":"posa","year":"0","journal-title":"Proc Workshop Algorithmic Found Robot"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-94-011-5014-9_23"},{"key":"ref22","first-page":"1","article-title":"End-to-end training of deep visuomotor\n policies","volume":"17","author":"levine","year":"2016","journal-title":"J Mach Learn Res"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2005.860248"},{"article-title":"Proximal policy optimization algorithms","year":"2017","author":"schulman","key":"ref24"},{"key":"ref23","first-page":"1889","article-title":"Trust region policy optimization","author":"schulman","year":"0","journal-title":"Proceedings of the 32nd Intl Conf on Machine Learning"},{"key":"ref26","volume":"28","author":"westervelt","year":"2007","journal-title":"Feedback Control of Dynamic Bipedal Robot Locomotion"},{"article-title":"Rigid body dynamics library","year":"2016","author":"felis","key":"ref25"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7083369\/8386768\/08423489.pdf?arnumber=8423489","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,26]],"date-time":"2022-01-26T13:15:58Z","timestamp":1643202958000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8423489\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,10]]},"references-count":27,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/lra.2018.2861466","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"type":"electronic","value":"2377-3766"},{"type":"electronic","value":"2377-3774"}],"subject":[],"published":{"date-parts":[[2018,10]]}}}