{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,23]],"date-time":"2026-03-23T13:00:14Z","timestamp":1774270814473,"version":"3.50.1"},"reference-count":42,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,10,24]],"date-time":"2020-10-24T00:00:00Z","timestamp":1603497600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,10,24]],"date-time":"2020-10-24T00:00:00Z","timestamp":1603497600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,10,24]],"date-time":"2020-10-24T00:00:00Z","timestamp":1603497600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100004830","name":"Siemens","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004830","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000006","name":"Office of Naval Research","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000006","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020,10,24]]},"DOI":"10.1109\/iros45743.2020.9340848","type":"proceedings-article","created":{"date-parts":[[2021,3,15]],"date-time":"2021-03-15T14:49:56Z","timestamp":1615819796000},"page":"9728-9735","source":"Crossref","is-referenced-by-count":63,"title":["Meta-Reinforcement Learning for Robotic Industrial Insertion Tasks"],"prefix":"10.1109","author":[{"given":"Gerrit","family":"Schoettler","sequence":"first","affiliation":[]},{"given":"Ashvin","family":"Nair","sequence":"additional","affiliation":[]},{"given":"Juan Aparicio","family":"Ojea","sequence":"additional","affiliation":[]},{"given":"Sergey","family":"Levine","sequence":"additional","affiliation":[]},{"given":"Eugen","family":"Solowjow","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","first-page":"3988","article-title":"Learning to learn by gradient descent by gradient descent","author":"andrychowicz","year":"2016","journal-title":"NeurIPS"},{"key":"ref38","article-title":"RL$ˆ2$: Fast Reinforcement Learning via Slow Reinforcement Learning","author":"duan","year":"2016"},{"key":"ref33","article-title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks","author":"finn","year":"2017","journal-title":"ICML"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793789"},{"key":"ref31","article-title":"Environment Probing Interaction Policies","author":"zhou","year":"2019","journal-title":"International Conference on Learning Representations"},{"key":"ref30","article-title":"Active Domain Randomization","author":"mehta","year":"2019","journal-title":"Conference on Robot Learning (CoRL)"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00691"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794310"},{"key":"ref35","article-title":"Universal Planning Networks","author":"srinivas","year":"2018","journal-title":"ICML"},{"key":"ref34","article-title":"Recasting Gradient-Based Meta-Learning As Hierarchical Bayes","author":"grant","year":"2018","journal-title":"ICLRE"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793506"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref11","doi-asserted-by":"crossref","first-page":"1607","DOI":"10.1609\/aaai.v24i1.7727","article-title":"Relative Entropy Policy Search","author":"peters","year":"2010","journal-title":"AAAI Conference on Artificial Intelligence"},{"key":"ref12","first-page":"1","article-title":"Playing Atari with Deep Reinforcement Learning","author":"mnih","year":"2013","journal-title":"NIPS Workshop on Deep Learning"},{"key":"ref13","doi-asserted-by":"crossref","first-page":"484","DOI":"10.1038\/nature16961","article-title":"Mastering the game of Go with deep neural networks and tree search","volume":"529","author":"silver","year":"2016","journal-title":"Nature"},{"key":"ref14","first-page":"1334","article-title":"End-to-End Training of Deep Visuomotor Policies","volume":"17","author":"levine","year":"2016","journal-title":"Journal of Machine Learning Research (JMLR)"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460655"},{"key":"ref16","article-title":"Reverse Curriculum Generation for Reinforcement Learning","author":"florensa","year":"2018","journal-title":"ICLRE"},{"key":"ref17","article-title":"Learning from Demonstrations for Real World Reinforcement Learning","author":"hester","year":"2018","journal-title":"AAAI Conference on Artificial Intelligence"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8463162"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.049"},{"key":"ref28","article-title":"Solving Rubik’s Cube with a Robot Hand","author":"akkaya","year":"2019"},{"key":"ref4","first-page":"1","article-title":"Intuitive peg-in-hole assembly strategy with a compliant manipulator","author":"park","year":"2013","journal-title":"IEEE ISR 2013"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.008"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2001.977187"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-94568-2_12"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2019.XV.029"},{"key":"ref5","first-page":"5331","article-title":"Efficient off-policy meta-reinforcement learning via probabilistic context variables","author":"rakelly","year":"2019","journal-title":"ICML"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989043"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2014.6943123"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1115\/1.3149634"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202244"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1115\/1.3427095"},{"key":"ref20","article-title":"Deep Reinforcement Learning for Industrial Insertion Tasks with Visual Inputs and Natural Rewards","author":"schoettler","year":"2019"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794127"},{"key":"ref21","article-title":"Leveraging Demonstrations for Deep Reinforcement Learning on Robotics Problems with Sparse Rewards","author":"ve?er\u00edk","year":"2017","journal-title":"CoRR"},{"key":"ref42","article-title":"Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor","author":"haarnoja","year":"2018","journal-title":"ICML"},{"key":"ref24","article-title":"CAD 2 RL: Real Single-Image Flight Without a Single Real Image","author":"sadeghi","year":"2017","journal-title":"RSS"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3150225"},{"key":"ref23","article-title":"Residual Policy Learning","author":"silver","year":"2018"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460528"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202133"}],"event":{"name":"2020 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","location":"Las Vegas, NV, USA","start":{"date-parts":[[2020,10,24]]},"end":{"date-parts":[[2021,1,24]]}},"container-title":["2020 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9340668\/9340635\/09340848.pdf?arnumber=9340848","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,21]],"date-time":"2022-12-21T14:52:46Z","timestamp":1671634366000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9340848\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,10,24]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/iros45743.2020.9340848","relation":{},"subject":[],"published":{"date-parts":[[2020,10,24]]}}}