{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,21]],"date-time":"2026-01-21T07:24:44Z","timestamp":1768980284849,"version":"3.49.0"},"reference-count":39,"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":[{"name":"INVERSE Project","award":["101136067"],"award-info":[{"award-number":["101136067"]}]},{"DOI":"10.13039\/501100000780","name":"European Commission","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000780","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2024,10]]},"DOI":"10.1109\/lra.2024.3443496","type":"journal-article","created":{"date-parts":[[2024,8,14]],"date-time":"2024-08-14T17:42:30Z","timestamp":1723657350000},"page":"8427-8434","source":"Crossref","is-referenced-by-count":4,"title":["Unsupervised Meta-Testing With Conditional Neural Processes for Hybrid Meta-Reinforcement Learning"],"prefix":"10.1109","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1901-8473","authenticated-orcid":false,"given":"Suzan Ece","family":"Ada","sequence":"first","affiliation":[{"name":"Department of Computer Engineering, Bogazici University, Istanbul, Türkiye"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9597-2731","authenticated-orcid":false,"given":"Emre","family":"Ugur","sequence":"additional","affiliation":[{"name":"Department of Computer Engineering, Bogazici University, Istanbul, Türkiye"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"ref2","article-title":"Playing atari with deep reinforcement learning","author":"Mnih","year":"2013"},{"key":"ref3","article-title":"A survey of meta-reinforcement learning","author":"Beck","year":"2023"},{"key":"ref4","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","author":"Finn","year":"2017"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2023.3250269"},{"key":"ref6","first-page":"323","article-title":"NoRML: No-reward meta learning","volume-title":"Proc. 18th Int. Conf. Auton. Agents Multiagent Syst.","author":"Yang","year":"2019"},{"key":"ref7","article-title":"Learning to adapt in dynamic, real-world environments through meta-reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Clavera","year":"2019"},{"key":"ref8","first-page":"5757","article-title":"Context-aware dynamics model for generalization in model-based reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Lee","year":"2020"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2021.xvii.011"},{"key":"ref10","first-page":"5331","article-title":"Efficient off-policy meta-reinforcement learning via probabilistic context variables","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Rakelly","year":"2019"},{"key":"ref11","article-title":"VariBAD: A very good method for bayes-adaptive deep RL via meta-learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zintgraf","year":"2020"},{"key":"ref12","article-title":"Evolutionary principles in self-referential learningdiploma thesis","author":"Schmidhuber","year":"1987","journal-title":"Technische Universitt Mnchen"},{"key":"ref13","article-title":"ProMP: Proximal meta-policy search","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Rothfuss","year":"2018"},{"key":"ref14","first-page":"31059","article-title":"A theoretical understanding of gradient bias in meta-reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Liu","year":"2022"},{"key":"ref15","article-title":"A simple neural attentive meta-learner","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Mishra","year":"2018"},{"key":"ref16","article-title":"One-shot imitation learning","volume-title":"Adv. Neural Inf. Process. Syst.","volume":"30","author":"Duan","year":"2017"},{"key":"ref17","article-title":"Meta-reinforcement learning of structured exploration strategies","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","volume":"31","author":"Gupta","year":"2018"},{"key":"ref18","article-title":"Meta-SGD: Learning to learn quickly for few-shot learning","author":"Li","year":"2017"},{"key":"ref19","article-title":"Multimodal model-agnostic meta-learning via task-aware modulation","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","volume":"32","author":"Vuorio","year":"2019"},{"key":"ref20","first-page":"1704","article-title":"Conditional neural processes","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Garnelo","year":"2018"},{"key":"ref21","article-title":"Focal: Efficient fully-offline meta-reinforcement learning via distance metric learning and behavior regularization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Li","year":"2020"},{"key":"ref22","article-title":"Auto-encoding variational bayes","volume-title":"Proc. 2nd Int. Conf. Learn. Representations","author":"Kingma","year":"2014"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2024.106201"},{"key":"ref24","article-title":"Autoregressive conditional neural processes","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Bruinsma","year":"2023"},{"key":"ref25","article-title":"Attentive neural processes","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kim","year":"2019"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00946"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2019.xv.071"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2021.11.004"},{"key":"ref29","article-title":"Generative adversarial networks with conditional neural movement primitives for an interactive generative drawing tool","author":"Ada","year":"2021"},{"key":"ref30","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton","year":"2018"},{"key":"ref31","article-title":"High-dimensional continuous control using generalized advantage estimation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Schulman","year":"2016"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1017\/S0263574722000625"},{"key":"ref33","first-page":"1","article-title":"Adam: A method for stochastic gradient descent","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma","year":"2015"},{"key":"ref34","article-title":"Deep reinforcement learning in a handful of trials using probabilistic dynamics models","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","volume":"31","author":"Chua","year":"2018"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref36","article-title":"Openai gym","author":"Brockman","year":"2016"},{"key":"ref37","article-title":"CaDM code repository","author":"Seo","year":"2020"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/0005-1098(89)90002-2"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/B978-0-444-53859-8.00003-5"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7083369\/10638067\/10636269.pdf?arnumber=10636269","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,30]],"date-time":"2024-08-30T10:27:50Z","timestamp":1725013670000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10636269\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10]]},"references-count":39,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/lra.2024.3443496","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10]]}}}