{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,26]],"date-time":"2026-06-26T14:39:59Z","timestamp":1782484799883,"version":"3.54.5"},"reference-count":47,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"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":[[2020,5]]},"DOI":"10.1109\/icra40945.2020.9197125","type":"proceedings-article","created":{"date-parts":[[2020,9,15]],"date-time":"2020-09-15T17:25:46Z","timestamp":1600190746000},"page":"7505-7512","source":"Crossref","is-referenced-by-count":46,"title":["Guided Uncertainty-Aware Policy Optimization: Combining Learning and Model-Based Strategies for Sample-Efficient Policy Learning"],"prefix":"10.1109","author":[{"given":"Michelle A.","family":"Lee","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Carlos","family":"Florensa","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jonathan","family":"Tremblay","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nathan","family":"Ratliff","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Animesh","family":"Garg","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fabio","family":"Ramos","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dieter","family":"Fox","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","article-title":"Model based training, detection and pose estimation of texture-less 3D objects in heavily cluttered scenes","author":"hinterstoisser","year":"2012","journal-title":"ACCV"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793542"},{"key":"ref33","article-title":"Making Sense of Vision and Touch: SelfSupervised Learning of Multimodal Representations for Contact-Rich Tasks","author":"lee","year":"2018"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460756"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460696"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2890449"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8463162"},{"key":"ref36","article-title":"Goal-conditioned Imitation Learning","author":"ding","year":"0"},{"key":"ref35","first-page":"1","article-title":"Leveraging¨ Demonstrations for Deep Reinforcement Learning on Robotics Problems with Sparse Rewards","author":"vecerik","year":"2017"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794102"},{"key":"ref10","article-title":"Experimental studies of contact space model for multi-surface collisions in articulated rigid-body systems","author":"ganguly","year":"2018","journal-title":"International Symposium on Experimental Robotics"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2017.103"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7139778"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2013.IX.031"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511546877"},{"key":"ref14","article-title":"Universal Value Function Approximators","author":"schaul","year":"0"},{"key":"ref15","article-title":"Automatic Goal Generation for Reinforcement Learning Agents","author":"florensa","year":"0"},{"key":"ref16","first-page":"1","article-title":"Reverse Curriculum Generation for Reinforcement Learning","author":"florensa","year":"0"},{"key":"ref17","article-title":"Benchmarking Deep Reinforcement Learning for Continuous Control","author":"duan","year":"0"},{"key":"ref18","first-page":"1","article-title":"Stochastic Neural Networks for Hierarchical Reinforcement Learning","author":"florensa","year":"0"},{"key":"ref19","article-title":"Deep object pose estimation for semantic robotic grasping of household objects","author":"tremblay","year":"2018","journal-title":"arXiv preprint arXiv 1809 10790"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2013.6696810"},{"key":"ref4","article-title":"Visual Reinforcement Learning with Imagined Goals","author":"nair","year":"2018","journal-title":"Adavances in Neural Information Processing Systems"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1177\/0278364917710318"},{"key":"ref3","article-title":"Posecnn: A convolutional neural network for 6d object pose estimation in cluttered scenes","author":"xiang","year":"2017","journal-title":"arXiv preprint arXiv 1711 07128"},{"key":"ref6","article-title":"Closing the sim-to-real loop: Adapting simulation randomization with real world experience","author":"chebotar","year":"2018","journal-title":"arXiv preprint arXiv 1810 06008"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2018.2791591"},{"key":"ref5","first-page":"1","article-title":"End-to-End Training of Deep Visuomotor Policies","volume":"17","author":"levine","year":"2016"},{"key":"ref8","article-title":"Residual Policy Learning","author":"silver","year":"2018"},{"key":"ref7","article-title":"Riemannian Motion Policies","author":"ratliff","year":"2018"},{"key":"ref2","article-title":"RMPflow : A Computational Graph for Automatic Motion Policy Generation","author":"cheng","year":"0","journal-title":"Tech Rep"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794127"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2014.X.030"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00038"},{"key":"ref20","article-title":"A General Safety Framework for Learning-Based Control in Uncertain Robotic Systems","author":"fisac","year":"2017"},{"key":"ref45","article-title":"Implicit 3d orientation learning for 6d object detection from rgb images","author":"sundermeyer","year":"2018","journal-title":"ECCV"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-008-0152-6"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-008-0152-6"},{"key":"ref21","article-title":"NDDS: NVIDIA deep learning dataset synthesizer","author":"to","year":"2018"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.019"},{"key":"ref24","first-page":"1","article-title":"Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor","author":"haarnoja","year":"2018","journal-title":"InInternational Conference on Machine Learning"},{"key":"ref41","article-title":"DPOD: Dense 6D pose object detector in RGB images","author":"zakharov","year":"2019","journal-title":"arXiv preprint arXiv 1902 10869"},{"key":"ref23","article-title":"Variable impedance control in end-effector space: An action space for reinforcement learning in contact-rich tasks","author":"mart\u00b4?n-mart\u00b4?n","year":"2019","journal-title":"arXiv preprint arXiv 1906 03008"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00469"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2018.07.006"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00350"},{"key":"ref25","first-page":"1","article-title":"VAE: LEARNING BASIC VISUAL CONCEPTS WITH A CONSTRAINED VARIATIONAL FRAMEWORK","volume":"11","author":"higgins","year":"0"}],"event":{"name":"2020 IEEE International Conference on Robotics and Automation (ICRA)","location":"Paris, France","start":{"date-parts":[[2020,5,31]]},"end":{"date-parts":[[2020,8,31]]}},"container-title":["2020 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9187508\/9196508\/09197125.pdf?arnumber=9197125","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,27]],"date-time":"2022-06-27T20:24:51Z","timestamp":1656361491000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9197125\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":47,"URL":"https:\/\/doi.org\/10.1109\/icra40945.2020.9197125","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}