{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,29]],"date-time":"2026-07-29T20:29:25Z","timestamp":1785356965462,"version":"3.55.0"},"reference-count":40,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,5,29]],"date-time":"2023-05-29T00:00:00Z","timestamp":1685318400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,5,29]],"date-time":"2023-05-29T00:00:00Z","timestamp":1685318400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100005017","name":"Regional Development and Energy (StMWi)","doi-asserted-by":"publisher","award":["DIK0249"],"award-info":[{"award-number":["DIK0249"]}],"id":[{"id":"10.13039\/501100005017","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,5,29]]},"DOI":"10.1109\/icra48891.2023.10160626","type":"proceedings-article","created":{"date-parts":[[2023,7,4]],"date-time":"2023-07-04T17:20:56Z","timestamp":1688491256000},"page":"5985-5991","source":"Crossref","is-referenced-by-count":11,"title":["Meta-Reinforcement Learning via Language Instructions"],"prefix":"10.1109","author":[{"given":"Zhenshan","family":"Bing","sequence":"first","affiliation":[{"name":"Technical University of Munich,Department of Informatics,Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alexander","family":"Koch","sequence":"additional","affiliation":[{"name":"Technical University of Munich,Department of Informatics,Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiangtong","family":"Yao","sequence":"additional","affiliation":[{"name":"Technical University of Munich,Department of Informatics,Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kai","family":"Huang","sequence":"additional","affiliation":[{"name":"School of Data and Computer Science, Sun Yat-sen University,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alois","family":"Knoll","sequence":"additional","affiliation":[{"name":"Technical University of Munich,Department of Informatics,Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3088947"},{"key":"ref35","article-title":"Investigating contingency awareness using atari 2600 games","author":"bellemare","year":"2012","journal-title":"Twenty-Sixth AAAI Conference on Artificial Intelligence"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2022.3172754"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref15","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":"ref37","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","author":"finn","year":"2017","journal-title":"Int Conference on Machine Learning"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3124366"},{"key":"ref36","first-page":"4045","article-title":"Time limits in reinforcement learning","author":"pardo","year":"2018","journal-title":"Int Conference on Machine Learning"},{"key":"ref31","doi-asserted-by":"crossref","first-page":"1532","DOI":"10.3115\/v1\/D14-1162","article-title":"Glove: Global vectors for word representation","author":"pennington","year":"2014","journal-title":"Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)"},{"key":"ref30","first-page":"1113","article-title":"Learning latent plans from play","volume":"100","author":"lynch","year":"2020","journal-title":"Proceedings of the Conference on Robot Learning ser Proceedings of Machine Learning Research"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2021.3121312"},{"key":"ref33","article-title":"Learning values across many orders of magnitude","volume":"29","author":"van hasselt","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2020.05.029"},{"key":"ref32","doi-asserted-by":"crossref","first-page":"1532","DOI":"10.3115\/v1\/D14-1162","article-title":"Glove: Global vectors for word representation","author":"pennington","year":"2014","journal-title":"Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)"},{"key":"ref2","article-title":"Dota 2 with large scale deep reinforcement learning","author":"berner","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref1","doi-asserted-by":"crossref","first-page":"350","DOI":"10.1038\/s41586-019-1724-z","article-title":"Grandmaster level in starcraft ii using multi-agent reinforcement learning","volume":"575","author":"vinyals","year":"2019","journal-title":"Nature"},{"key":"ref17","article-title":"Solving rubik's cube with a robot hand","author":"akkaya","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref39","first-page":"5331","article-title":"Efficient off-policy meta-reinforcement learning via probabilistic context variables","author":"rakelly","year":"2019","journal-title":"Int Conference on Machine Learning"},{"key":"ref16","article-title":"Hindsight experience replay","volume":"30","author":"andrychowicz","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref38","author":"duan","year":"2017","journal-title":"RL?2 Fast reinforcement learning via slow reinforcement learning"},{"key":"ref19","article-title":"Learning to reinforcement learn","author":"wang","year":"2016","journal-title":"ArXiv Preprint"},{"key":"ref18","author":"duan","year":"2017","journal-title":"RL\/\\2 Fast reinforcement learning via slow reinforcement learning"},{"key":"ref24","first-page":"5331","article-title":"Efficient off-policy meta-reinforcement learning via probabilistic context variables","author":"rakelly","year":"2019","journal-title":"Int Conference on Machine Learning"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i8.26210"},{"key":"ref26","article-title":"Learning from symmetry: Meta-reinforcement learning with symmetric data and language instructions","author":"yao","year":"2022","journal-title":"ArXiv Preprint"},{"key":"ref25","first-page":"1094","article-title":"Meta-world: A benchmark and evaluation for multi-task and meta reinforcement learning","author":"yu","year":"2020","journal-title":"Conference on Robot Learning"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.tics.2019.02.006"},{"key":"ref22","article-title":"Meta-reinforcement learning in broad and non-parametric environments","author":"bing","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3185549"},{"key":"ref28","first-page":"13139","article-title":"Language-conditioned imitation learning for robot manipulation tasks","volume":"33","author":"stepputtis","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1177\/02783649211046285"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981810"},{"key":"ref8","article-title":"Soft actor-critic algorithms and applications","author":"haarnoja","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref7","first-page":"1889","article-title":"Trust region policy optimization","author":"schulman","year":"2015","journal-title":"Int Conference on Machine Learning"},{"key":"ref9","article-title":"Distributed distributional deterministic policy gradients","author":"barth-maron","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref4","article-title":"Mastering chess and shogi by self-play with a general reinforcement learning algorithm","author":"silver","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/MRA.2022.3204237"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460482"},{"key":"ref40","article-title":"Learning to reinforcement learn","author":"wang","year":"2016","journal-title":"ArXiv Preprint"}],"event":{"name":"2023 IEEE International Conference on Robotics and Automation (ICRA)","location":"London, United Kingdom","start":{"date-parts":[[2023,5,29]]},"end":{"date-parts":[[2023,6,2]]}},"container-title":["2023 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10160211\/10160212\/10160626.pdf?arnumber=10160626","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,24]],"date-time":"2023-07-24T17:37:25Z","timestamp":1690220245000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10160626\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5,29]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/icra48891.2023.10160626","relation":{},"subject":[],"published":{"date-parts":[[2023,5,29]]}}}