{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T10:01:01Z","timestamp":1776852061795,"version":"3.51.2"},"reference-count":48,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Aviation Foundation of the National Key Laboratory of Air-Based Information Perception and Fusion","award":["ASFC-20240001070002"],"award-info":[{"award-number":["ASFC-20240001070002"]}]},{"name":"Open-End Foundation of the National Key Laboratory of Air-Based Information Perception and Fusion 6A"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2026,3]]},"DOI":"10.1109\/tnnls.2025.3614724","type":"journal-article","created":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T18:03:10Z","timestamp":1761847390000},"page":"1477-1491","source":"Crossref","is-referenced-by-count":1,"title":["Enhancing the Policy Generalization on OOD Tasks via Latent Variable Distribution Enhancement Sampler"],"prefix":"10.1109","volume":"37","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-8470-010X","authenticated-orcid":false,"given":"Shaobo","family":"Li","sequence":"first","affiliation":[{"name":"Xi’an Jiaotong University, Xi’an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3476-110X","authenticated-orcid":false,"given":"Jie","family":"Lin","sequence":"additional","affiliation":[{"name":"Xi’an Jiaotong University, Xi’an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3036-6022","authenticated-orcid":false,"given":"Xiangyuan","family":"Yang","sequence":"additional","affiliation":[{"name":"Xi’an Jiaotong University, Xi’an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8869-6863","authenticated-orcid":false,"given":"Hanlin","family":"Zhang","sequence":"additional","affiliation":[{"name":"Qingdao University, Qingdao, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7033-9315","authenticated-orcid":false,"given":"Peng","family":"Zhao","sequence":"additional","affiliation":[{"name":"Xi’an Jiaotong University, Xi’an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton","year":"2018"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3236361"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3459991"},{"key":"ref4","first-page":"486","article-title":"A theoretical analysis of deep Q-learning","volume-title":"Proc. Learn. Dyn. Control","author":"Yang"},{"key":"ref5","first-page":"1","article-title":"Model-based reinforcement learning for Atari","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Kaiser"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-020-03051-4"},{"key":"ref7","article-title":"Learning to reinforcement learn","author":"X Wang","year":"2016","journal-title":"arXiv:1611.05763"},{"key":"ref8","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":"Nagabandi"},{"key":"ref9","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":"ref10","first-page":"1","article-title":"Meta-learning and universality: Deep representations and gradient descent can approximate any learning algorithm","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Finn"},{"key":"ref11","article-title":"Some considerations on learning to explore via meta-reinforcement learning","author":"Stadie","year":"2018","journal-title":"arXiv:1803.01118"},{"key":"ref12","first-page":"1","article-title":"ProMP: Proximal meta-policy search","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Rothfuss"},{"key":"ref13","first-page":"1","article-title":"How to train your MAML","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Antoniou"},{"key":"ref14","first-page":"113","article-title":"Meta-learning with implicit gradients","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Rajeswaran"},{"key":"ref15","first-page":"1","article-title":"Recasting gradient-based meta-learning as hierarchical Bayes","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Grant"},{"key":"ref16","article-title":"RL2: Fast reinforcement learning via slow reinforcement learning","author":"Duan","year":"2016","journal-title":"arXiv:1611.02779"},{"key":"ref17","first-page":"12448","article-title":"Generalization of reinforcement learners with working and episodic memory","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Fortunato"},{"key":"ref18","first-page":"1","article-title":"Rapid task-solving in novel environments","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Ritter"},{"key":"ref19","first-page":"5331","article-title":"Efficient off-policy meta-reinforcement learning via probabilistic context variables","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Rakelly"},{"issue":"289","key":"ref20","first-page":"1","article-title":"VariBAD: Variational Bayes-adaptive deep RL via meta-learning","volume":"22","author":"Zintgraf","year":"2021","journal-title":"J. Mach. Learn. Res."},{"key":"ref21","first-page":"734","article-title":"Fast adaptation via policy-dynamics value functions","volume-title":"Proc. 37th Int. Conf. Mach. Learn. (ICML)","author":"Raileanu"},{"key":"ref22","article-title":"Meta-reinforcement learning robust to distributional shift via model identification and experience relabeling","author":"Mendonca","year":"2020","journal-title":"arXiv:2006.07178"},{"key":"ref23","first-page":"27222","article-title":"Improving generalization in meta-RL with imaginary tasks from latent dynamics mixture","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lee"},{"key":"ref24","first-page":"43356","article-title":"Parameterizing non-parametric meta-reinforcement learning tasks via subtask decomposition","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Lee"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3417114"},{"key":"ref26","first-page":"1","article-title":"On the practical consistency of meta-reinforcement learning algorithms","volume-title":"Proc. 5th Workshop Meta-Learn. Conf. Neural Inf. Process. Syst.","author":"Xiong"},{"key":"ref27","first-page":"73","article-title":"Estimating disentangled belief about hidden state and hidden task for meta-reinforcement learning","volume-title":"Proc. 3rd Conf. Learn. Dyn. Control","author":"Akuzawa"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2714"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.4324\/9780203469569-35"},{"key":"ref30","article-title":"Meta reinforcement learning as task inference","author":"Humplik","year":"2019","journal-title":"arXiv:1905.06424"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2025.3533035"},{"key":"ref32","first-page":"13956","article-title":"Generalization in reinforcement learning with selective noise injection and information bottleneck","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Igl"},{"key":"ref33","first-page":"1","article-title":"Network randomization: A simple technique for generalization in deep reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Lee"},{"key":"ref34","first-page":"19884","article-title":"Reinforcement learning with augmented data","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Laskin"},{"key":"ref35","first-page":"59832","article-title":"Learning better with less: Effective augmentation for sample-efficient visual reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ma"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02142"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01524"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1137\/21M1445831"},{"key":"ref39","article-title":"Kernel density Bayesian inverse reinforcement learning","author":"Mandyam","year":"2023","journal-title":"arXiv:2303.06827"},{"key":"ref40","article-title":"Improved exploring starts by kernel density estimation-based state-space coverage acceleration in reinforcement learning","author":"Schenke","year":"2021","journal-title":"arXiv:2105.08990"},{"key":"ref41","first-page":"9444","article-title":"Robust kernel density estimation with median-of-means principle","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Humbert"},{"key":"ref42","first-page":"40605","article-title":"KDEformer: Accelerating transformers via kernel density estimation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zandieh"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1201\/9781315140919"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/7503.003.0022"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"ref46","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref48","first-page":"1094","article-title":"Meta-world: A benchmark and evaluation for multi-task and meta reinforcement learning","volume-title":"Proc. Conf. Robot Learn. (CoRL)","author":"Yu"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/5962385\/11418705\/11222616.pdf?arnumber=11222616","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,3]],"date-time":"2026-03-03T20:53:31Z","timestamp":1772571211000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11222616\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3]]},"references-count":48,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2025.3614724","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3]]}}}