{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,25]],"date-time":"2025-06-25T04:06:30Z","timestamp":1750824390941,"version":"3.41.0"},"reference-count":33,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["2305486"],"award-info":[{"award-number":["2305486"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Inform. Theory"],"published-print":{"date-parts":[[2025,7]]},"DOI":"10.1109\/tit.2025.3569421","type":"journal-article","created":{"date-parts":[[2025,5,12]],"date-time":"2025-05-12T17:43:42Z","timestamp":1747071822000},"page":"5601-5619","source":"Crossref","is-referenced-by-count":0,"title":["Asymptotic Analysis of Sample-Averaged Q-Learning"],"prefix":"10.1109","volume":"71","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-2399-2387","authenticated-orcid":false,"given":"Saunak Kumar","family":"Panda","sequence":"first","affiliation":[{"name":"Department of Industrial and Systems Engineering, University of Houston, Houston, TX, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9392-3071","authenticated-orcid":false,"given":"Ruiqi","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Mathematics and Statistics, Texas Tech University, Lubbock, TX, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0696-2924","authenticated-orcid":false,"given":"Yisha","family":"Xiang","sequence":"additional","affiliation":[{"name":"Department of Industrial and Systems Engineering, University of Houston, Houston, TX, USA"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.2307\/2171758"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2743240"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1002\/SERIES1345"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s12045-013-0136-x"},{"key":"ref5","article-title":"The ODE method for asymptotic statistics in stochastic approximation and reinforcement learning","author":"Borkar","year":"2021","journal-title":"arXiv:2110.14427"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.2020.1826325"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1214\/18-AOS1801"},{"key":"ref8","article-title":"Online statistical inference for contextual bandits via stochastic gradient descent","author":"Chen","year":"2022","journal-title":"arXiv:2212.14883"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1017\/cbo9780511802256"},{"key":"ref10","article-title":"Fastest convergence for Q-learning","author":"Devraj","year":"2017","journal-title":"arXiv:1707.03770"},{"issue":"6","key":"ref11","first-page":"1","article-title":"An invariance principle for certain probability limit theorems","volume":"6","author":"Donsker","year":"1951","journal-title":"Memoirs Amer. Math. Soc."},{"key":"ref12","first-page":"1","article-title":"Online bootstrap confidence intervals for the stochastic gradient descent estimator","volume":"19","author":"Fang","year":"2018","journal-title":"J. Mach. Learn. Res."},{"key":"ref13","first-page":"1","article-title":"Statistical properties of reinforcement learning algorithms","volume":"18","author":"Gadat","year":"2018","journal-title":"J. Mach. Learn. Res."},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/tit.2024.3386122"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1111\/rssb.12050"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913495721"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1137\/s0363012901385691"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i7.20701"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1287\/opre.2023.2450"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2021.3120096"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11686"},{"key":"ref22","first-page":"2207","article-title":"A statistical analysis of Polyak\u2013Ruppert averaged Q-learning","volume-title":"Proc. 26th Int. Conf. Artif. Intell. Statist.","author":"Li"},{"key":"ref23","article-title":"Statistical inference with stochastic gradient methods under \u03a6-mixing data","author":"Liu","year":"2023","journal-title":"arXiv:2302.12717"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.3150\/18-BEJ1088"},{"volume-title":"Machine Learning: A Probabilistic Perspective","year":"2012","author":"Murphy","key":"ref25"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.2022.2096620"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/BF02771562"},{"issue":"124","key":"ref28","first-page":"1","article-title":"HiGrad: Uncertainty quantification for online learning and stochastic approximation","volume":"24","author":"Su","year":"2023","journal-title":"J. Mach. Learn. Res."},{"volume-title":"Reinforcement Learning: An Introduction","year":"2018","author":"Sutton","key":"ref29"},{"key":"ref30","article-title":"Variance-reduced Q-learning is minimax optimal","author":"Wainwright","year":"2019","journal-title":"arXiv:1906.04697"},{"key":"ref31","first-page":"8998","article-title":"A statistical online inference approach in averaged stochastic approximation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Xie"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1214\/aop\/1176988849"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/WSC52266.2021.9715437"}],"container-title":["IEEE Transactions on Information Theory"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/18\/11045245\/11002555.pdf?arnumber=11002555","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,24]],"date-time":"2025-06-24T07:05:31Z","timestamp":1750748731000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11002555\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7]]},"references-count":33,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tit.2025.3569421","relation":{},"ISSN":["0018-9448","1557-9654"],"issn-type":[{"type":"print","value":"0018-9448"},{"type":"electronic","value":"1557-9654"}],"subject":[],"published":{"date-parts":[[2025,7]]}}}