{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T15:20:10Z","timestamp":1759332010810,"version":"3.37.3"},"reference-count":33,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100010664","name":"European Union\u2019s Horizon 2020 Framework Program for Research and Innovation within the \u201cHuman Brain Project Specific Grant Agreement (SGA3)\u201d","doi-asserted-by":"publisher","award":["945539"],"award-info":[{"award-number":["945539"]}],"id":[{"id":"10.13039\/100010664","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61902442"],"award-info":[{"award-number":["61902442"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2024,10]]},"DOI":"10.1109\/tnnls.2023.3270298","type":"journal-article","created":{"date-parts":[[2023,5,24]],"date-time":"2023-05-24T17:43:44Z","timestamp":1684950224000},"page":"13604-13618","source":"Crossref","is-referenced-by-count":18,"title":["Meta-Reinforcement Learning in Nonstationary and Nonparametric Environments"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0896-2517","authenticated-orcid":false,"given":"Zhenshan","family":"Bing","sequence":"first","affiliation":[{"name":"Department of Informatics, Technical University of Munich, Munich, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lukas","family":"Knak","sequence":"additional","affiliation":[{"name":"Department of Informatics, Technical University of Munich, Munich, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9993-0077","authenticated-orcid":false,"given":"Long","family":"Cheng","sequence":"additional","affiliation":[{"name":"College of Computer Science and Artificial Intelligence, Wenzhou University, Wenzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0185-7420","authenticated-orcid":false,"given":"Fabrice O.","family":"Morin","sequence":"additional","affiliation":[{"name":"Department of Informatics, Technical University of Munich, Munich, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0359-7810","authenticated-orcid":false,"given":"Kai","family":"Huang","sequence":"additional","affiliation":[{"name":"School of Data and Computer Science, Sun Yat-sen University, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4840-076X","authenticated-orcid":false,"given":"Alois","family":"Knoll","sequence":"additional","affiliation":[{"name":"Department of Informatics, Technical University of Munich, Munich, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.13140\/RG.2.2.18893.74727"},{"key":"ref2","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2019.XV.011"},{"key":"ref4","article-title":"Solving Rubik\u2019s cube with a robot hand","author":"Akkaya","year":"2019","journal-title":"arXiv:1910.07113"},{"key":"ref5","article-title":"RL2: Fast reinforcement learning via slow reinforcement learning","author":"Duan","year":"2016","journal-title":"arXiv:1611.02779"},{"key":"ref6","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","volume":"70","author":"Finn"},{"key":"ref7","article-title":"Learning to reinforcement learn","author":"Wang","year":"2016","journal-title":"arXiv:1611.05763"},{"key":"ref8","first-page":"5331","article-title":"Efficient off-policy meta-reinforcement learning via probabilistic context variables","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","volume":"97","author":"Rakelly"},{"key":"ref9","first-page":"1","article-title":"Learning context-aware task reasoning for efficient meta-reinforcement learning","volume-title":"Proc. AAMAS","author":"Wang"},{"key":"ref10","article-title":"Meta reinforcement learning as task inference","author":"Humplik","year":"2019","journal-title":"arXiv:1905.06424"},{"key":"ref11","first-page":"1","article-title":"Deep online learning via meta-learning: Continual adaptation for model-based RL","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Nagabandi"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/387"},{"key":"ref13","first-page":"5","article-title":"Context-based meta-reinforcement learning with structured latent space","volume-title":"Proc. Skills Workshop NeurIPS","author":"Ren"},{"key":"ref14","article-title":"Meta-world: A benchmark and evaluation for multi-task and meta reinforcement learning","author":"Yu","year":"2019","journal-title":"arXiv:1910.10897"},{"key":"ref15","first-page":"1","article-title":"Learning to adapt in dynamic, real-world environments through meta-reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Clavera"},{"key":"ref16","first-page":"1","article-title":"Continual unsupervised representation learning","volume-title":"Proc. NeurIPS","author":"Rao"},{"key":"ref17","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proc. ICML","volume":"80","author":"Haarnoja"},{"key":"ref18","first-page":"1","article-title":"Continuous adaptation via meta-learning in nonstationary and competitive environments","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Al-Shedivat"},{"key":"ref19","article-title":"Learning to adapt in dynamic, real-world environments through meta-reinforcement learning","author":"Nagabandi","year":"2018","journal-title":"arXiv:1803.11347"},{"key":"ref20","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","volume-title":"Proc. 33rd Int. Conf. Mach. Learn.","volume":"48","author":"Mnih"},{"key":"ref21","first-page":"1","article-title":"VariBAD: A very good method for Bayes-adaptive deep RL via meta-learning","volume-title":"Proc. ICLR","author":"Zintgraf"},{"key":"ref22","first-page":"5307","article-title":"Meta-reinforcement learning of structured exploration strategies","volume-title":"Proc. 32nd Int. Conf. Neural Inf. Process. Syst.","author":"Gupta"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3105407"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2021.3121432"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3079148"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3070584"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1312.6114"},{"key":"ref29","article-title":"Deep unsupervised clustering with Gaussian mixture variational autoencoders","author":"Dilokthanakul","year":"2016","journal-title":"arXiv:1611.02648"},{"key":"ref30","first-page":"1","article-title":"ProMP: Proximal meta-policy search","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Rothfuss"},{"issue":"11","key":"ref31","first-page":"1","article-title":"Visualizing data using t-SNE","volume":"9","author":"Van Der Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"ref32","article-title":"OpenAI Gym","author":"Brockman","year":"2016","journal-title":"arXiv:1606.01540"},{"key":"ref33","first-page":"1","article-title":"A simple neural attentive meta-learner","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Mishra"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/10707065\/10132404.pdf?arnumber=10132404","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,8]],"date-time":"2024-10-08T05:24:21Z","timestamp":1728365061000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10132404\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10]]},"references-count":33,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2023.3270298","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"type":"print","value":"2162-237X"},{"type":"electronic","value":"2162-2388"}],"subject":[],"published":{"date-parts":[[2024,10]]}}}