{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,3]],"date-time":"2026-05-03T05:55:22Z","timestamp":1777787722066,"version":"3.51.4"},"reference-count":31,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"European Union IntelliLung Project","award":["101057434"],"award-info":[{"award-number":["101057434"]}]},{"name":"infrastructure provided by German Federal Ministry of Education and Research","award":["SCADS22B"],"award-info":[{"award-number":["SCADS22B"]}]},{"name":"Saxon State Ministry for Science, Culture and Tourism"},{"name":"Competence Center for Big Data and AI through the Center for Scalable Data Analytics and Artificial Intelligence (ScaDS.AI), Dresden\/Leipzig"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/access.2026.3685907","type":"journal-article","created":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T19:50:24Z","timestamp":1776801024000},"page":"61867-61880","source":"Crossref","is-referenced-by-count":0,"title":["Test-Time Confidence Quantification Using Q-Ensembles for Offline RL"],"prefix":"10.1109","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-3686-3902","authenticated-orcid":false,"given":"Jason","family":"Li","sequence":"first","affiliation":[{"name":"Nature-Inspired Machine Intelligence Research Group, Institute for Applied Informatics (InfAI) e.V., Dresden, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Muhammad Hamza","family":"Yousuf","sequence":"additional","affiliation":[{"name":"Nature-Inspired Machine Intelligence Research Group, Institute for Applied Informatics (InfAI) e.V., Dresden, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-3852-0355","authenticated-orcid":false,"given":"Juhyun","family":"Seo","sequence":"additional","affiliation":[{"name":"Nature-Inspired Machine Intelligence Research Group, Institute for Applied Informatics (InfAI) e.V., Dresden, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jens","family":"Lehmann","sequence":"additional","affiliation":[{"name":"Nature-Inspired Machine Intelligence Research Group, Institute for Applied Informatics (InfAI) e.V., Dresden, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sahar","family":"Vahdati","sequence":"additional","affiliation":[{"name":"Nature-Inspired Machine Intelligence Research Group, Institute for Applied Informatics (InfAI) e.V., Dresden, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3477600"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-018-0213-5"},{"issue":"2","key":"ref3","first-page":"65","article-title":"Ventilator weaning and spontaneous breathing trials; an educational review","volume":"4","author":"Zein","year":"2016","journal-title":"Nat. Inst. Health (NIH)"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1378\/chest.116.suppl_1.9S-a"},{"key":"ref5","first-page":"7167","article-title":"A simple unified framework for detecting out-of-distribution samples and adversarial attacks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lee"},{"key":"ref6","first-page":"6402","article-title":"Simple and scalable predictive uncertainty estimation using deep ensembles","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lakshminarayanan"},{"key":"ref7","article-title":"A baseline for detecting misclassified and out-of-distribution examples in neural networks","author":"Hendrycks","year":"2016","journal-title":"arXiv:1610.02136"},{"key":"ref8","article-title":"Deep anomaly detection with outlier exposure","author":"Hendrycks","year":"2018","journal-title":"arXiv:1812.04606"},{"key":"ref9","article-title":"Energy-based out-of-distribution detection","author":"Liu","year":"2020","journal-title":"arXiv:2010.03759"},{"key":"ref10","article-title":"Statistical analysis of nearest neighbor methods for anomaly detection","author":"Gu","year":"2019","journal-title":"arXiv:1907.03813"},{"key":"ref11","first-page":"1530","article-title":"Variational inference with normalizing flows","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Rezende"},{"key":"ref12","article-title":"Do deep generative models know what they don\u2019t know?","author":"Nalisnick","year":"2018","journal-title":"arXiv:1810.09136"},{"key":"ref13","article-title":"Bayesian deep learning and a probabilistic perspective of generalization","author":"Gordon Wilson","year":"2020","journal-title":"arXiv:2002.08791"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aiide.v18i1.21959"},{"key":"ref15","article-title":"Deep exploration via bootstrapped DQN","author":"Osband","year":"2016","journal-title":"arXiv:1602.04621"},{"key":"ref16","article-title":"Sample-efficient reinforcement learning with stochastic ensemble value expansion","author":"Buckman","year":"2018","journal-title":"arXiv:1807.01675"},{"key":"ref17","first-page":"1179","article-title":"Conservative Q-learning for offline reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kumar"},{"key":"ref18","first-page":"7436","article-title":"Uncertainty-based offline reinforcement learning with diversified Q-ensemble","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"An"},{"key":"ref19","article-title":"Confidence-conditioned value functions for offline reinforcement learning","author":"Hong","year":"2022","journal-title":"arXiv:2212.04607"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i20.35410"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-021-00388-6"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i13.26862"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i27.35013"},{"key":"ref24","article-title":"Batch policy learning under constraints","author":"Le","year":"2019","journal-title":"arXiv:1903.08738"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1328"},{"key":"ref26","article-title":"D4RL: Datasets for deep data-driven reinforcement learning","author":"Fu","year":"2020","journal-title":"arXiv:2004.07219"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1038\/sdata.2018.178"},{"key":"ref28","article-title":"Advancing safe mechanical ventilation using offline RL with hybrid actions and clinically aligned rewards","author":"Hamza Yousuf","year":"2025","journal-title":"arXiv:2506.14375"},{"key":"ref29","article-title":"CORL: Research-oriented deep offline reinforcement learning library","volume-title":"Proc. 3rd Offline RL Workshop, Offline RL Launchpad","author":"Tarasov"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1161\/01.CTR.101.23.e215"},{"key":"ref31","first-page":"13991","article-title":"Can you trust your model\u2019s uncertainty? Evaluating predictive uncertainty under dataset shift","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Ovadia"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/11323511\/11488879.pdf?arnumber=11488879","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:51:49Z","timestamp":1777492309000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11488879\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/access.2026.3685907","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}