{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,21]],"date-time":"2026-10-21T14:32:00Z","timestamp":1792593120546,"version":"4.5.0"},"reference-count":38,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"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":[[2019,5]]},"DOI":"10.1109\/icra.2019.8794160","type":"proceedings-article","created":{"date-parts":[[2019,8,13]],"date-time":"2019-08-13T01:26:12Z","timestamp":1565659572000},"page":"2153-2160","source":"Crossref","is-referenced-by-count":25,"title":["Reinforcement Learning in Topology-based Representation for Human Body Movement with Whole Arm Manipulation"],"prefix":"10.1109","author":[{"given":"Weihao","family":"Yuan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kaiyu","family":"Hang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haoran","family":"Song","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Danica","family":"Kragic","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michael Y.","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Johannes A.","family":"Stork","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref38","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"arXiv preprint arXiv 1412 6980"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/1073204.1073219"},{"key":"ref32","author":"chung","year":"1997","journal-title":"Spectral Graph Theory American Mathematical Society"},{"key":"ref31","first-page":"975","article-title":"The self-linking number of a closed space curve","volume":"17","author":"pohl","year":"1968","journal-title":"Journal of Mathematics and Mechanics"},{"key":"ref30","article-title":"Learning Dexterous In-Hand Manipulation","year":"2018","journal-title":"arXiv preprint arXiv 1808 02194"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref36","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"International Conference on Machine Learning"},{"key":"ref35","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"arXiv preprint arXiv 1707 07816"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-29090-7_9"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.1988.12057"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-58069-7_9"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2000.844743"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.1993.292146"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2006.282370"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2010.5652787"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1002\/cav.376"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2013.6696782"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/HUMANOIDS.2014.7041437"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913482017"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202141"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7139621"},{"key":"ref27","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2015","journal-title":"arXiv preprint arXiv 1509 02971"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2011.6094737"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2010.5651652"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2017.XIII.058"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8462863"},{"key":"ref8","doi-asserted-by":"crossref","first-page":"1136","DOI":"10.1109\/IROS.2007.4399592","article-title":"Humanoid robot which can lift a 30kg box by whole body contact and tactile feedback","author":"ohmura","year":"2007","journal-title":"Intelligent Robots and Systems 2007 IROS 2007 IEEE\/RSJ International Conference on"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2014.6942771"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2017.2651381"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2007.363950"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2000.844081"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2000.846421"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2013.6630710"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/HUMANOIDS.2013.7029968"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/1778765.1778770"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2012.VIII.059"},{"key":"ref26","doi-asserted-by":"crossref","first-page":"354","DOI":"10.1038\/nature24270","article-title":"Mastering the game of go without human knowledge","volume":"550","author":"silver","year":"2017","journal-title":"Nature"},{"key":"ref25","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"}],"event":{"name":"2019 International Conference on Robotics and Automation (ICRA)","location":"Montreal, QC, Canada","start":{"date-parts":[[2019,5,20]]},"end":{"date-parts":[[2019,5,24]]}},"container-title":["2019 International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8780387\/8793254\/08794160.pdf?arnumber=8794160","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,15]],"date-time":"2022-07-15T03:15:10Z","timestamp":1657854910000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8794160\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,5]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/icra.2019.8794160","relation":{},"subject":[],"published":{"date-parts":[[2019,5]]}}}