{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,28]],"date-time":"2026-02-28T17:50:17Z","timestamp":1772301017927,"version":"3.50.1"},"reference-count":49,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100010418","name":"Institute of Information Communications Technology Planning Evaluation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100010418","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Korean Government","award":["2022-0-00469"],"award-info":[{"award-number":["2022-0-00469"]}]},{"name":"KT Corporation as part of the Korea Telecom (KT)-Korea Advanced Institute of Science and Technology (KAIST) Open Research and Development Project"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/access.2024.3476564","type":"journal-article","created":{"date-parts":[[2024,10,9]],"date-time":"2024-10-09T17:52:26Z","timestamp":1728496346000},"page":"149916-149939","source":"Crossref","is-referenced-by-count":2,"title":["Finite-Time Analysis of Asynchronous Q-Learning Under Diminishing Step-Size From Control-Theoretic View"],"prefix":"10.1109","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1515-5836","authenticated-orcid":false,"given":"Han-Dong","family":"Lim","sequence":"first","affiliation":[{"name":"Department of Electrical Engineering, KAIST, Daejeon, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4962-8478","authenticated-orcid":false,"given":"Donghwan","family":"Lee","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering, KAIST, Daejeon, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref2","first-page":"1","article-title":"Recurrent experience replay in distributed reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Kapturowski"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-020-03051-4"},{"key":"ref4","article-title":"Never give up: Learning directed exploration strategies","author":"Badia","year":"2020","journal-title":"arXiv:2002.06038"},{"key":"ref5","first-page":"507","article-title":"Agent57: Outperforming the Atari human benchmark","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Badia"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3543846"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913495721"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/IntelliSys.2017.8324237"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/BF00993306"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21236\/ada276517"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1137\/S0363012997331639"},{"key":"ref13","first-page":"1","article-title":"A unified switching system perspective and convergence analysis of Q-learning algorithms","volume-title":"Proc. 34th Conf. Neural Inf. Process. Syst. (NeurIPS)","author":"Lee"},{"key":"ref14","first-page":"1065","article-title":"The asymptotic convergence-rate of Q-learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Szepesv\u00e1ri"},{"issue":"1","key":"ref15","first-page":"1","article-title":"Learning rates for Q-learning","volume":"5","author":"Even-Dar","year":"2003","journal-title":"J. Mach. Learn. Res."},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1137\/22M1489976"},{"key":"ref17","first-page":"7031","article-title":"Sample complexity of asynchronous Q-learning: Sharper analysis and variance reduction","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Li"},{"key":"ref18","article-title":"A Lyapunov theory for finite-sample guarantees of asynchronous Q-learning and TD-learning variants","author":"Chen","year":"2021","journal-title":"arXiv:2102.01567"},{"key":"ref19","first-page":"3185","article-title":"Finite-time analysis of asynchronous stochastic approximation and Q-learning","volume-title":"Proc. Conf. Learn. Theory","author":"Qu"},{"key":"ref20","first-page":"6296","article-title":"Tightening the dependence on horizon in the sample complexity of Q-learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2024.3355326"},{"key":"ref22","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4612-0017-8","volume-title":"Switching in Systems and Control","volume":"190","author":"Liberzon","year":"2003"},{"key":"ref23","volume-title":"Nonlinear Systems","author":"Khalil","year":"2002"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.1995.478953"},{"key":"ref25","first-page":"582","article-title":"Periodic Q-learning","volume-title":"Proc. 2nd Conf. Learn. Dyn. Control","author":"Lee"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.sysconle.2012.08.014"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.2013.6580117"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-93-86279-38-5"},{"key":"ref29","volume-title":"Stochastic Approximation and Recursive Algorithms and Applications","volume":"35","author":"Kushner","year":"2003"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4471-4285-0"},{"key":"ref31","first-page":"8477","article-title":"Characterizing the exact behaviors of temporal difference learning algorithms using Markov jump linear system theory","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Hu"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/BF00115009"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/9.664150"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2013.09.038"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2008.2012009"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2017.2689499"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4612-2046-6"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1090\/mbk\/107"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177729586"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1137\/070704277"},{"key":"ref41","first-page":"1","article-title":"On Markov chain gradient descent","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Sun"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1287\/opre.2020.2024"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1137\/110836043"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1214\/EJP.v20-4039"},{"key":"ref45","first-page":"8223","article-title":"Finite-sample analysis of contractive stochastic approximation using smooth convex envelopes","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Chen"},{"key":"ref46","first-page":"1","article-title":"Double Q-learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Hasselt"},{"key":"ref47","volume-title":"Matrix Analysis","author":"Horn","year":"2013"},{"key":"ref48","volume-title":"Introduction to Algorithms","author":"Cormen","year":"2022"},{"key":"ref49","volume-title":"Probabilistic Graphical Models: Principles and Techniques","author":"Koller","year":"2009"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10380310\/10711190.pdf?arnumber=10711190","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,18]],"date-time":"2024-10-18T17:33:40Z","timestamp":1729272820000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10711190\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":49,"URL":"https:\/\/doi.org\/10.1109\/access.2024.3476564","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}