{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T18:46:24Z","timestamp":1777488384589,"version":"3.51.4"},"reference-count":52,"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.2019.8794033","type":"proceedings-article","created":{"date-parts":[[2019,8,13]],"date-time":"2019-08-13T01:26:12Z","timestamp":1565659572000},"page":"3636-3643","source":"Crossref","is-referenced-by-count":30,"title":["Learning Deep Visuomotor Policies for Dexterous Hand Manipulation"],"prefix":"10.1109","author":[{"given":"Divye","family":"Jain","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andrew","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shivam","family":"Singhal","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Aravind","family":"Rajeswaran","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vikash","family":"Kumar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Emanuel","family":"Todorov","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"International Conference on Machine Learning"},{"key":"ref38","first-page":"1531","article-title":"A natural policy gradient","author":"kakade","year":"2002","journal-title":"Advances in neural information processing systems"},{"key":"ref33","article-title":"Universal planning networks","volume":"abs 1804 645","author":"srinivas","year":"2018","journal-title":"CoRR"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.009"},{"key":"ref31","article-title":"Overcoming exploration in reinforcement learning with demonstrations","volume":"abs 1709 10089","author":"nair","year":"2017","journal-title":"CoRR"},{"key":"ref30","article-title":"Deep imitation learning for complex manipulation tasks from virtual reality teleoperation","volume":"abs 1710 4615","author":"zhang","year":"2017","journal-title":"CoRR"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"ref36","author":"kumar","year":"2016","journal-title":"Manipulators and manipulation in high dimensional spaces"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989384"},{"key":"ref28","article-title":"Learning hand-eye coordination for robotic grasping with deep learning and large-scale data collection","volume":"abs 1603 2199","author":"levine","year":"2016","journal-title":"CoRR"},{"key":"ref27","article-title":"Sim-to-real robot learning from pixels with progressive nets","author":"rusu","year":"2017","journal-title":"CoRL"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487517"},{"key":"ref2","year":"2018","journal-title":"Learning Dexterous in-Hand Manipulation"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.049"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-010-5223-6"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2014.6943031"},{"key":"ref21","article-title":"Dexterous Manipulation with Deep Reinforcement Learning: Efficient, General, and Low-Cost","volume":"abs 1810 6045","author":"zhu","year":"2018","journal-title":"CoRR"},{"key":"ref24","author":"mudigonda","year":"2018","journal-title":"Investigating deep reinforcement learning for grasping objects with an anthropomorphic hand"},{"key":"ref23","article-title":"Learning awareness models","volume":"abs 1804 6318","author":"amos","year":"2018","journal-title":"CoRR"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202133"},{"key":"ref25","article-title":"(CAD)2RL: Real Single-Image Flight without a Single Real Image","author":"sadeghi","year":"2016","journal-title":"Arxive-prints"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref52","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"NIPS"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2016.7759557"},{"key":"ref11","first-page":"137","article-title":"Contact-invariant optimization for hand manipulation","author":"mordatch","year":"2012","journal-title":"SIGGRAPH Symposium on Computer Animation"},{"key":"ref40","article-title":"High-dimensional continuous control using generalized advantage estimation","author":"schulman","year":"2016","journal-title":"International Conference on Learning Representations"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2014.6907864"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913506757"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2015.7354126"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TOH.2012.53"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TRA.2003.814499"},{"key":"ref17","article-title":"Graspit! a versatile simulator for robotic grasping","author":"miller","year":"2004","journal-title":"IEEE Robotics & Automation Magazine"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1201\/9781315136370"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/HUMANOIDS.2015.7363524"},{"key":"ref4","article-title":"EPOpt: Learning Robust Neural Network Policies Using Model Ensembles","author":"rajeswaran","year":"2017","journal-title":"ICLRE"},{"key":"ref3","article-title":"Plan Online, Learn Offline: Efficient Learning and Exploration via Model-Based Control","author":"lowrey","year":"2019","journal-title":"ICLRE"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/SIMPAR.2018.8376268"},{"key":"ref5","article-title":"Sim-to-real transfer of robotic control with dynamics randomization","volume":"abs 1710 6537","author":"peng","year":"2017","journal-title":"CoRR"},{"key":"ref8","article-title":"Sim-to-real: Learning agile locomotion for quadruped robots","volume":"abs 1804 10332","author":"tan","year":"2018","journal-title":"CoRR"},{"key":"ref49","article-title":"A reduction of imitation learning and structured prediction to no-regret online learning","author":"ross","year":"2011","journal-title":"AISTATS"},{"key":"ref7","article-title":"Asymmetric actor critic for image-based robot learning","volume":"abs 1710 6542","author":"pinto","year":"2017","journal-title":"CoRR"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1177\/0278364915592961"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386025"},{"key":"ref45","article-title":"Emergence of locomotion behaviours in rich environments","volume":"abs 1707 2286","author":"heess","year":"2017","journal-title":"CoRR"},{"key":"ref48","doi-asserted-by":"crossref","DOI":"10.1145\/3197517.3201311","article-title":"Deepmimic: Example-guided deep reinforcement learning of physics-based character skills","author":"peng","year":"2018","journal-title":"ACM SIGGRAPH"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2012.325"},{"key":"ref42","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2016","journal-title":"International Conference on Learning Representations"},{"key":"ref41","article-title":"Towards Generalization and Simplicity in Continuous Control","author":"rajeswaran","year":"2017","journal-title":"NIPS"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8463162"},{"key":"ref43","author":"kakade","year":"2003","journal-title":"On the sample complexity of reinforcement learning"}],"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\/08794033.pdf?arnumber=8794033","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\/8794033\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,5]]},"references-count":52,"URL":"https:\/\/doi.org\/10.1109\/icra.2019.8794033","relation":{},"subject":[],"published":{"date-parts":[[2019,5]]}}}