{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,6]],"date-time":"2026-07-06T12:11:11Z","timestamp":1783339871725,"version":"3.54.6"},"reference-count":56,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,9,27]],"date-time":"2021-09-27T00:00:00Z","timestamp":1632700800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,9,27]],"date-time":"2021-09-27T00:00:00Z","timestamp":1632700800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,9,27]],"date-time":"2021-09-27T00:00:00Z","timestamp":1632700800000},"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":[[2021,9,27]]},"DOI":"10.1109\/iros51168.2021.9636477","type":"proceedings-article","created":{"date-parts":[[2021,12,16]],"date-time":"2021-12-16T20:45:38Z","timestamp":1639687538000},"page":"3619-3626","source":"Crossref","is-referenced-by-count":20,"title":["Joint Space Control via Deep Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Visak","family":"Kumar","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"David","family":"Hoeller","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Balakumar","family":"Sundaralingam","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jonathan","family":"Tremblay","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Stan","family":"Birchfield","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/72.80212"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/HUMANOIDS.2017.8246876"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/671"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201311"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2934906"},{"key":"ref30","article-title":"On the power of curriculum learning in training deep networks","author":"hacohen","year":"2019","journal-title":"ICML"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/HUMANOIDS.2015.7363544"},{"key":"ref36","article-title":"How much do unstated problem constraints limit deep robotic reinforcement learning?","author":"lewis","year":"2019","journal-title":"Technical Report TR Rice University"},{"key":"ref35","article-title":"GPU-accelerated robotics simulation for distributed reinforcement learning","author":"liang","year":"2018","journal-title":"CoRL"},{"key":"ref34","first-page":"1","article-title":"Curriculum learning for reinforcement learning domains: A framework and survey","volume":"21","author":"narvekar","year":"2020","journal-title":"JMLR"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995523"},{"key":"ref27","article-title":"Self-paced learning for latent variable models","author":"kumar","year":"2010","journal-title":"NeurIPS"},{"key":"ref29","article-title":"Reverse curriculum generation for reinforcement learning","author":"florensa","year":"2017","journal-title":"CoRL"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1177\/0278364908091463"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/JRA.1987.1087068"},{"key":"ref20","article-title":"PointNet: Deep learning on point sets for 3D classification and segmentation","author":"qi","year":"2017","journal-title":"CVPR"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8967695"},{"key":"ref21","article-title":"PointNet++: Deep hierarchical feature learning on point sets in a metric space","author":"qi","year":"2017","journal-title":"NeurIPS"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2006.890271"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00589"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.cognition.2008.11.014"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553380"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2001.973374"},{"key":"ref51","article-title":"Sim2Real view invariant visual servoing by recurrent control","author":"sadeghi","year":"2018","journal-title":"CVPR"},{"key":"ref56","author":"de wit","year":"2012","journal-title":"Theory of Robot Control"},{"key":"ref55","article-title":"Reinforcement learning experiments and benchmark for solving robotic reaching tasks","author":"aumjaud","year":"2020"},{"key":"ref54","article-title":"QT-Opt: Scalable deep reinforcement learning for vision-based robotic manipulation","author":"kalashnikov","year":"2018","journal-title":"CoRL"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197125"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197134"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793485"},{"key":"ref11","article-title":"OpenAI gym","author":"brockman","year":"2016"},{"key":"ref40","article-title":"Learning global direct inverse kinematics","author":"demers","year":"1992","journal-title":"NeurIPS"},{"key":"ref12","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017"},{"key":"ref13","article-title":"Temporal difference models: Model-free deep RL for model-based control","author":"pong","year":"2018","journal-title":"CoRL"},{"key":"ref14","article-title":"End-to-end training of deep visuomotor policies","author":"levine","year":"2016","journal-title":"JMLR"},{"key":"ref15","article-title":"Sim2Real view invariant visual servoing by recurrent control","author":"sadeghi","year":"2018","journal-title":"CVPR"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.009"},{"key":"ref17","article-title":"Benchmarking reinforcement learning algorithms on real-world robots","author":"mahmood","year":"2018","journal-title":"CoRL"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN48605.2020.9207427"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.23919\/ECC.2019.8796030"},{"key":"ref4","first-page":"441","article-title":"RMPflow: A computational graph for automatic motion policy generation","author":"cheng","year":"2018","journal-title":"WAFR"},{"key":"ref3","article-title":"Riemannian motion policies","author":"ratliff","year":"2018"},{"key":"ref6","first-page":"1329","article-title":"Benchmarking deep reinforcement learning for continuous control","author":"duan","year":"2016","journal-title":"ICML"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2795645"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2965875"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2020.XVI.082"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593833"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8968201"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793789"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1177\/0278364907087548"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2011.6094666"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.aau5872"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/70.294207"},{"key":"ref41","article-title":"A real-time learning neural robot controller","author":"van der smagt","year":"1991","journal-title":"ICANN"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2007.363633"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2006.II.033"}],"event":{"name":"2021 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","location":"Prague, Czech Republic","start":{"date-parts":[[2021,9,27]]},"end":{"date-parts":[[2021,10,1]]}},"container-title":["2021 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9635848\/9635849\/09636477.pdf?arnumber=9636477","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T16:54:53Z","timestamp":1652201693000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9636477\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,9,27]]},"references-count":56,"URL":"https:\/\/doi.org\/10.1109\/iros51168.2021.9636477","relation":{},"subject":[],"published":{"date-parts":[[2021,9,27]]}}}