{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,20]],"date-time":"2025-09-20T21:14:05Z","timestamp":1758402845392,"version":"3.28.0"},"reference-count":40,"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.2019.8793556","type":"proceedings-article","created":{"date-parts":[[2019,8,12]],"date-time":"2019-08-12T21:26:12Z","timestamp":1565645172000},"page":"36-42","source":"Crossref","is-referenced-by-count":11,"title":["VPE: Variational Policy Embedding for Transfer Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Isac","family":"Atnekvist","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Danica","family":"Kragic","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Johannes A.","family":"Stork","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","article-title":"Parameter space noise for exploration","author":"plappert","year":"2018","journal-title":"International Conference on Learning Representations"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1080\/00401706.1962.10490022"},{"key":"ref32","first-page":"4287","article-title":"Learning values across many orders of magnitude","author":"van hasselt","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref31","article-title":"How to train deep variational autoencoders and probabilistic ladder networks","author":"s\u00f8nderby","year":"2016","journal-title":"arXiv preprint arXiv 1602 00377"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-662-38527-2_55"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1512\/iumj.1957.6.56038"},{"journal-title":"OpenAI Gym","year":"2016","author":"brockman","key":"ref36"},{"journal-title":"Bayesian optimization","year":"2018","author":"nogueira","key":"ref35"},{"key":"ref34","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"arXiv preprint arXiv 1412 6980"},{"key":"ref10","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","author":"finn","year":"2017","journal-title":"arXiv preprint arXiv 1703 06870"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2015.7353536"},{"key":"ref11","article-title":"Reptile: a scalable metalearning algorithm","author":"nichol","year":"2018","journal-title":"arXiv preprint arXiv 1803 02999"},{"journal-title":"Deep q-embedding for transfer reinforcement learning","year":"2017","author":"neitz","key":"ref12"},{"key":"ref13","article-title":"Learning an embedding space for transferable robot skills","author":"hausman","year":"2018","journal-title":"International Conference on Learning Representations"},{"key":"ref14","first-page":"1087","article-title":"One-shot imitation learning","author":"duan","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref15","first-page":"1235","article-title":"Multi-modal imitation learning from unstructured demonstrations using generative adversarial nets","author":"hausman","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref16","first-page":"4565","article-title":"Generative adversarial imitation learning","author":"ho","year":"2016","journal-title":"Advances in Neural IInformation Processing Systems"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/425"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2009.191"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/168304.168306"},{"key":"ref4","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2015","journal-title":"arXiv preprint arXiv 1509 02971"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2012.2218595"},{"key":"ref3","first-page":"1334","article-title":"End-to-end training of deep visuomotor policies","volume":"17","author":"levine","year":"2016","journal-title":"The Journal of Machine Learning Research"},{"key":"ref6","article-title":"Using simulation and domain adaptation to improve efficiency of deep robotic grasping","author":"bousmalis","year":"2017","journal-title":"arXiv preprint arXiv 1709 04396"},{"key":"ref29","first-page":"2348","article-title":"Practical variational inference for neural networks","author":"graves","year":"2011","journal-title":"Advances in neural information processing systems"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2743240"},{"key":"ref8","article-title":"Reinforcement learning for pivoting task","author":"antonova","year":"2017","journal-title":"arXiv preprint arXiv 1703 06870"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202133"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2016.2535302"},{"key":"ref1","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":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.222"},{"key":"ref22","first-page":"1633","article-title":"Transfer learning for reinforcement learning domains: A survey","volume":"10","author":"taylor","year":"2009","journal-title":"Journal of Machine Learning Research"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref24","first-page":"1825","article-title":"The numerics of gans","author":"mescheder","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref23","first-page":"2672","article-title":"Generative adversarial nets","author":"goodfellow","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1023\/A:1007665907178"},{"journal-title":"Reinforcement learning An introduction Second edition","year":"2017","author":"sutton","key":"ref25"}],"event":{"name":"2019 International Conference on Robotics and Automation (ICRA)","start":{"date-parts":[[2019,5,20]]},"location":"Montreal, QC, Canada","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\/08793556.pdf?arnumber=8793556","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,14]],"date-time":"2022-07-14T23:08:11Z","timestamp":1657840091000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8793556\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,5]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/icra.2019.8793556","relation":{},"subject":[],"published":{"date-parts":[[2019,5]]}}}