{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,27]],"date-time":"2026-07-27T10:26:04Z","timestamp":1785147964589,"version":"3.55.0"},"reference-count":43,"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:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2024,10]]},"DOI":"10.1109\/tpami.2024.3386780","type":"journal-article","created":{"date-parts":[[2024,4,9]],"date-time":"2024-04-09T18:23:03Z","timestamp":1712686983000},"page":"6948-6965","source":"Crossref","is-referenced-by-count":13,"title":["Context-Based Meta-Reinforcement Learning With Bayesian Nonparametric Models"],"prefix":"10.1109","volume":"46","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, München, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-4397-1538","authenticated-orcid":false,"given":"Yuqi","family":"Yun","sequence":"additional","affiliation":[{"name":"Department of Informatics, Technical University of Munich, München, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0359-7810","authenticated-orcid":false,"given":"Kai","family":"Huang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"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, München, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Finn"},{"key":"ref2","article-title":"Learning to adapt in dynamic, real-world environments through meta-reinforcement learning","author":"Nagabandi","year":"2018"},{"key":"ref3","article-title":"RL$^{2}$2: Fast reinforcement learning via slow reinforcement learning","author":"Duan","year":"2016"},{"key":"ref4","article-title":"Learning to reinforcement learn","author":"Wang","year":"2016"},{"key":"ref5","first-page":"5331","article-title":"Efficient off-policy meta-reinforcement learning via probabilistic context variables","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Rakelly"},{"key":"ref6","article-title":"VariBAD: A very good method for Bayes-adaptive deep RL via meta-learning","author":"Zintgraf","year":"2019"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3185549"},{"key":"ref8","first-page":"1094","article-title":"Meta-world: A benchmark and evaluation for multi-task and meta reinforcement learning","volume-title":"Proc. Conf. Robot Learn.","author":"Yu"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/623"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4419-8020-5"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.tics.2019.02.006"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1126\/science.aaz7597"},{"key":"ref13","article-title":"Self-labelling via simultaneous clustering and representation learning","author":"Asano","year":"2019"},{"key":"ref14","first-page":"478","article-title":"Unsupervised deep embedding for clustering analysis","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Xie"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-71246-8_49"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00996"},{"key":"ref17","article-title":"Deep robust clustering by contrastive learning","author":"Zhong","year":"2020"},{"key":"ref18","article-title":"Stick-breaking variational autoencoders","author":"Nalisnick","year":"2016"},{"key":"ref19","first-page":"1133","article-title":"Memoized online variational inference for Dirichlet process mixture models","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Hughes"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3085891"},{"key":"ref21","article-title":"Continuous adaptation via meta-learning in nonstationary and competitive environments","author":"Al-Shedivat","year":"2017"},{"key":"ref22","first-page":"12 600","article-title":"MetaCURE: Meta reinforcement learning with empowerment-driven exploration","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhang"},{"key":"ref23","article-title":"Learning context-aware task reasoning for efficient meta-reinforcement learning","author":"Wang","year":"2020"},{"key":"ref24","first-page":"5","article-title":"Context-based meta-reinforcement learning with structured latent space","volume-title":"Proc. Skills Workshop Neural Inf. Process. Syst.","author":"Ren"},{"key":"ref25","article-title":"Deep online learning via meta-learning: Continual adaptation for model-based RL","author":"Nagabandi","year":"2018"},{"key":"ref26","first-page":"9119","article-title":"Reconciling meta-learning and continual learning with online mixtures of tasks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Jerfel"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3055499"},{"key":"ref28","first-page":"280","article-title":"Dirichlet process","volume":"1063","author":"Teh","year":"2010","journal-title":"Encyclopedia Mach. Learn."},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21236\/ada238689"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.jmp.2011.08.004"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1214\/aos\/1176342360"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1198\/1061860043001"},{"key":"ref33","first-page":"876","article-title":"Sequential Monte Carlo samplers for Dirichlet process mixtures","volume-title":"Proc. 13th Int. Conf. Artif. Intell. Statist.","author":"Ulker"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1214\/06-BA104"},{"key":"ref35","article-title":"Understanding variational autoencoders","author":"Rocca","year":"2019"},{"key":"ref36","article-title":"Soft actor-critic algorithms and applications","author":"Haarnoja","year":"2018"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2211477"},{"key":"ref38","article-title":"Stick-breaking variational autoencoders","author":"Nalisnick","year":"2017"},{"key":"ref39","article-title":"Deep unsupervised clustering with Gaussian mixture variational autoencoders","author":"Dilokthanakul","year":"2017"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/273"},{"issue":"11","key":"ref41","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"Van der Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"ref42","article-title":"OpenAI gym","author":"Brockman","year":"2016"},{"key":"ref43","article-title":"ProMP: Proximal meta-policy search","author":"Rothfuss","year":"2018"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/10666888\/10495171.pdf?arnumber=10495171","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,7]],"date-time":"2024-09-07T04:42:46Z","timestamp":1725684166000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10495171\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10]]},"references-count":43,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2024.3386780","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10]]}}}