{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T15:30:35Z","timestamp":1759332635457,"version":"3.28.0"},"reference-count":23,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2015,9]]},"DOI":"10.1109\/iros.2015.7354297","type":"proceedings-article","created":{"date-parts":[[2015,12,17]],"date-time":"2015-12-17T16:52:55Z","timestamp":1450371175000},"page":"6435-6442","source":"Crossref","is-referenced-by-count":17,"title":["Learning compound multi-step controllers under unknown dynamics"],"prefix":"10.1109","author":[{"given":"Weiqiao","family":"Han","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sergey","family":"Levine","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pieter","family":"Abbeel","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2008.02.003"},{"key":"ref11","article-title":"Reinforcement learning of motor skills in high dimensions","author":"theodorou","year":"2010","journal-title":"International Conference on Robotics and Automation (ICRA)"},{"key":"ref12","article-title":"Learning neural network policies with guided policy search under unknown dynamics","author":"levine","year":"2014","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"ref13","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1561\/2300000021","article-title":"A survey on policy search for robotics","volume":"2","author":"deisenroth","year":"2013","journal-title":"Foundations and Trends in Robotics"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2012.2210294"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2013.6630937"},{"key":"ref16","article-title":"Learning manipulation by sequencing motor primitives with a two-armed robot","author":"lioutikov","year":"2014","journal-title":"International Conference on Intelligent Autonomous Systems (IAS)"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2014.6943187"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1177\/0278364911428653"},{"key":"ref19","article-title":"Skill discovery in continuous reinforcement learning domains using skill chaining","author":"konidaris","year":"2009","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2004.1307456"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2011.VII.008"},{"key":"ref6","article-title":"Fast biped walking with a reflexive controller and realtime policy searching","author":"geng","year":"2006","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2004.1389841"},{"key":"ref8","article-title":"Learning contact-rich manipulation skills with guided policy search","author":"levine","year":"2015","journal-title":"International Conference on Robotics and Automation (ICRA)"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1177\/0278364907084980"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2009.5152385"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2010.VI.005"},{"key":"ref9","first-page":"222","article-title":"Iterative linear quadratic regulator design for nonlinear biological movement systems","author":"li","year":"2004","journal-title":"ICINCO"},{"key":"ref20","article-title":"End-to-end training of deep visuomotor policies","author":"levine","year":"2015","journal-title":"arXiv preprint arXiv 1504 00702"},{"key":"ref22","article-title":"Guided policy search","author":"levine","year":"2013","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511804441"},{"key":"ref23","article-title":"Sample-based information-theoretic stochastic optimal control","author":"lioutikov","year":"2014","journal-title":"International Conference on Robotics and Automation (ICRA)"}],"event":{"name":"2015 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","start":{"date-parts":[[2015,9,28]]},"location":"Hamburg, Germany","end":{"date-parts":[[2015,10,2]]}},"container-title":["2015 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7347169\/7353104\/07354297.pdf?arnumber=7354297","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,6,23]],"date-time":"2017-06-23T21:56:16Z","timestamp":1498254976000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7354297\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,9]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/iros.2015.7354297","relation":{},"subject":[],"published":{"date-parts":[[2015,9]]}}}