{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T20:19:10Z","timestamp":1777407550568,"version":"3.51.4"},"reference-count":26,"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.2019.8794065","type":"proceedings-article","created":{"date-parts":[[2019,8,13]],"date-time":"2019-08-13T01:26:12Z","timestamp":1565659572000},"page":"2161-2167","source":"Crossref","is-referenced-by-count":38,"title":["Demonstration-Guided Deep Reinforcement Learning of Control Policies for Dexterous Human-Robot Interaction"],"prefix":"10.1109","author":[{"given":"Sammy","family":"Christen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Stefan","family":"Stevsic","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Otmar","family":"Hilliges","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Deepmimic: Example-guided deep reinforcement learning of physics-based character skills","author":"peng","year":"2018","journal-title":"arXiv preprint arXiv 1804 02671"},{"key":"ref11","first-page":"4565","article-title":"Generative adversarial imitation learning","author":"ho","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref12","article-title":"Learning human behaviors from motion capture by adversarial imitation","author":"merel","year":"2017","journal-title":"arXiv preprint arXiv 1707 01280"},{"key":"ref13","article-title":"Openai gym","volume":"abs 1606 1540","author":"brockman","year":"2016","journal-title":"CoRR"},{"key":"ref14","article-title":"Leveraging demonstrations for deep reinforcement learning on robotics problems with sparse rewards","author":"vecer?k","year":"2017","journal-title":"CoRR abs\/1707 08817"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2013.6630771"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2014.6907059"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2014.6907864"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487156"},{"key":"ref19","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2015","journal-title":"arXiv preprint arXiv 1509 02971"},{"key":"ref4","article-title":"Learning dexterous in-hand manipulation","author":"andrychowicz","year":"2018","journal-title":"arXiv preprint arXiv 1808 02194"},{"key":"ref3","first-page":"137","article-title":"Contact-invariant optimization for hand manipulation","author":"mordatch","year":"2012","journal-title":"Proceedings of the ACM SIG-GRAPH\/Eurographics symposium on computer animation Euro-graphics Association"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/HUMANOIDS.2016.7803388"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8206381"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989197"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8206333"},{"key":"ref2","article-title":"Learning complex dexterous manipulation with deep reinforcement learning and demonstrations","author":"rajeswaran","year":"2017","journal-title":"arXiv preprint arXiv 1709 10119"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCIS.2015.7274632"},{"key":"ref1","year":"2018","journal-title":"Shadow Dexterous Hand"},{"key":"ref20","first-page":"1889","article-title":"Trust region policy optimization","author":"schulman","year":"2015","journal-title":"International Conference on Machine Learning"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989385"},{"key":"ref21","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"arXiv preprint arXiv 1707 07816"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/1015330.1015430"},{"key":"ref23","first-page":"262","article-title":"Sim-to-real robot learning from pixels with progressive nets","author":"rusu","year":"2017","journal-title":"Conference on Robot Learning"},{"key":"ref26","article-title":"Maximum entropy deep inverse reinforcement learning","author":"wulfmeier","year":"2015","journal-title":"arXiv preprint arXiv 1507 04888"},{"key":"ref25","first-page":"1433","article-title":"Maximum entropy inverse reinforcement learning","author":"ziebart","year":"2008","journal-title":"AAAI"}],"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\/08794065.pdf?arnumber=8794065","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,15]],"date-time":"2022-07-15T03:13:25Z","timestamp":1657854805000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8794065\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,5]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/icra.2019.8794065","relation":{},"subject":[],"published":{"date-parts":[[2019,5]]}}}