{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T19:13:54Z","timestamp":1780514034591,"version":"3.54.1"},"reference-count":30,"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.2019.8794102","type":"proceedings-article","created":{"date-parts":[[2019,8,13]],"date-time":"2019-08-13T01:26:12Z","timestamp":1565659572000},"page":"3651-3657","source":"Crossref","is-referenced-by-count":125,"title":["Dexterous Manipulation with Deep Reinforcement Learning: Efficient, General, and Low-Cost"],"prefix":"10.1109","author":[{"given":"Henry","family":"Zhu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Abhishek","family":"Gupta","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aravind","family":"Rajeswaran","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sergey","family":"Levine","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vikash","family":"Kumar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref30","article-title":"Towards generalization and simplicity in continuous control","author":"rajeswaran","year":"2017","journal-title":"NIPS"},{"key":"ref10","article-title":"Contact-invariant op-timization for hand manipulation","author":"mordatch","year":"2012","journal-title":"Proceedings of the ACM SIGGRAPH\/Eurographics Symposium on Computer Animation Eurographics Association"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2014.6907059"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2014.6907864"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487156"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2016.7759557"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/HUMANOIDS.2015.7363524"},{"key":"ref16","first-page":"849","article-title":"Policy search for motor primitives in robotics","author":"kober","year":"2008","journal-title":"Advances in Neural Information Processing Systems 21 Proceedings of the Twenty-Second Annual Conference on Neural Information Processing Systems"},{"key":"ref17","author":"ijspeert","year":"2002","journal-title":"Learning Attractor Landscapes for Learning Motor Primitives"},{"key":"ref18","article-title":"Leveraging demonstrations for deep reinforcement learning on robotics problems with sparse rewards","volume":"abs 1707 8817","author":"vecerik","year":"2017","journal-title":"CoRR"},{"key":"ref19","article-title":"Overcoming exploration in reinforcement learning with demonstrations","volume":"abs 1709 10089","author":"nair","year":"2017","journal-title":"CoRR"},{"key":"ref28","article-title":"Trust region policy optimization","author":"schulman","year":"2015","journal-title":"Proceedings of the ICML International Conference on Machine Learning"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2000.844081"},{"key":"ref27","article-title":"Learning dexterous in-hand manipulation","volume":"abs 1808 177","year":"2018","journal-title":"CoRR"},{"key":"ref3","first-page":"109","article-title":"Dlr-hand II next generation of a dextrous robot hand","author":"butterfa\u00df","year":"2001","journal-title":"Proceedings of the 2001 IEEE International Conference on Robotics and Automation ICRA 2001"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TOH.2012.53"},{"key":"ref29","article-title":"Natural actor-critic","volume":"71","author":"peters","year":"0","journal-title":"Neurocomputing"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2000.844067"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/MRA.2004.1371616"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TRA.2003.814499"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2013.6630771"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1201\/9781315136370"},{"key":"ref1","article-title":"Learning complex dexterous manipulation with deep reinforcement learning and demonstrations","volume":"abs 1709 10087","author":"rajeswaran","year":"2017","journal-title":"CoRR"},{"key":"ref20","article-title":"Deep q-learning from demonstrations","author":"hester","year":"2018","journal-title":"Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence"},{"key":"ref22","article-title":"Epopt: Learning robust neural network policies using model ensembles","volume":"abs 1610 1283","author":"rajeswaran","year":"2016","journal-title":"CoRR"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.009"},{"key":"ref24","article-title":"Transferring end-to-end visuomotor control from simulation to real world for a multi-stage task","author":"james","year":"2017","journal-title":"Conference on Robot Learning (CoRL)"},{"key":"ref23","article-title":"(cad)$2$rl: Real single-image flight without a single real image","volume":"abs 1611 4201","author":"sadeghi","year":"2016","journal-title":"CoRR"},{"key":"ref26","article-title":"Sim-to-real: Learning agile locomotion for quadruped robots","volume":"abs 1804 10332","author":"tan","year":"2018","journal-title":"CoRR"},{"key":"ref25","article-title":"Sim2real view invariant visual servoing by recurrent control","volume":"abs 1712 7642","author":"sadeghi","year":"2017","journal-title":"CoRR"}],"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\/08794102.pdf?arnumber=8794102","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,15]],"date-time":"2022-07-15T03:17:50Z","timestamp":1657855070000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8794102\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,5]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/icra.2019.8794102","relation":{},"subject":[],"published":{"date-parts":[[2019,5]]}}}