{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,26]],"date-time":"2026-07-26T09:43:21Z","timestamp":1785059001910,"version":"3.55.0"},"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.2019.8793506","type":"proceedings-article","created":{"date-parts":[[2019,8,12]],"date-time":"2019-08-12T21:26:12Z","timestamp":1565645172000},"page":"3080-3087","source":"Crossref","is-referenced-by-count":157,"title":["Reinforcement Learning on Variable Impedance Controller for High-Precision Robotic Assembly"],"prefix":"10.1109","author":[{"given":"Jianlan","family":"Luo","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Eugen","family":"Solowjow","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chengtao","family":"Wen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Juan Aparicio","family":"Ojea","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alice M.","family":"Agogino","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aviv","family":"Tamar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pieter","family":"Abbeel","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref38","first-page":"1255","article-title":"Modeling Interaction via the Principle of Maximum Causal Entropy","author":"ziebart","year":"2010","journal-title":"Proceedings of the 27th International Conference on International Conference on Machine Learning ICML’10"},{"key":"ref33","first-page":"3132","article-title":"Interactive Control of Diverse Complex Characters with Neural Networks","author":"mordatch","year":"2015","journal-title":"Advances in Neural IInformation Processing Systems"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2015.7354126"},{"key":"ref31","first-page":"43:1","article-title":"Discovery of Complex Behaviors Through Contact-invariant Optimization","volume":"31 4","author":"mordatch","year":"2012","journal-title":"ACM Trans Graph"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2011.2159412"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.2005.1469949"},{"key":"ref36","author":"lynch","year":"2017","journal-title":"Modern Robotics Mechanics Planning and Control"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460696"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202244"},{"key":"ref10","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"International Conference on Machine Learning"},{"key":"ref11","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2015","journal-title":"arXiv preprint arXiv 1509 02971"},{"key":"ref12","first-page":"1","article-title":"An Application of Reinforcement Learning to Aerobatic Helicopter Flight","author":"abbeel","year":"2006","journal-title":"Proceedings of the 19th International Conference on Neural Information Processing Systems"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8463144"},{"key":"ref14","first-page":"1889","article-title":"Trust region policy optimization","author":"schulman","year":"2015","journal-title":"International Conference on Machine Learning"},{"key":"ref15","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":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487175"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7138994"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989384"},{"key":"ref19","first-page":"1607","article-title":"Relative Entropy Policy Search","author":"peters","year":"2010","journal-title":"AAAI"},{"key":"ref28","article-title":"Combining Model-Based and Model-Free Updates for Trajectory-Centric Reinforcement Learning","author":"chebotar","year":"2017","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref4","first-page":"1334","article-title":"End-to-end training of deep visuomotor policies","volume":"17 1","author":"levine","year":"2016","journal-title":"The Journal of Machine Learning Research"},{"key":"ref27","first-page":"4008","article-title":"Guided policy search via approximate mirror descent","author":"montgomery","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913495721"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1177\/0278364907087548"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2833142"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/JRA.1987.1087068"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1177\/0278364911402527"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1177\/0278364908091463"},{"key":"ref2","first-page":"1","article-title":"A survey on policy search for robotics","volume":"2 1 2","author":"deisenroth","year":"2013","journal-title":"Foundations and Trends in Robotics"},{"key":"ref9","article-title":"Playing atari with deep reinforcement learning","author":"mnih","year":"2013","journal-title":"arXiv preprint arXiv 1312 5602"},{"key":"ref1","volume":"1 1","author":"sutton","year":"1998","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2016.7759592"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1177\/0278364917743795"},{"key":"ref21","article-title":"Learning from the Hindsight Plan – Episodic MPC Improvement","author":"tamar","year":"2016","journal-title":"ArXiv e-prints"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8594353"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2015.XI.012"},{"key":"ref26","first-page":"1","article-title":"Guided policy search","author":"levine","year":"2013","journal-title":"International Conference on Machine Learning"},{"key":"ref25","author":"johannink","year":"0","journal-title":"Residual Reinforcement Learning for Robot Control"}],"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\/08793506.pdf?arnumber=8793506","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,14]],"date-time":"2022-07-14T23:10:23Z","timestamp":1657840223000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8793506\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,5]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/icra.2019.8793506","relation":{},"subject":[],"published":{"date-parts":[[2019,5]]}}}