{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,16]],"date-time":"2026-01-16T00:21:06Z","timestamp":1768522866360,"version":"3.49.0"},"reference-count":35,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2024,7,1]],"date-time":"2024-07-01T00:00:00Z","timestamp":1719792000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"name":"BK21 FOUR"},{"name":"Ministry of Education Republic of Korea"},{"name":"Institute of Information Communications Technology Planning Evaluation","award":["2022-0-00469"],"award-info":[{"award-number":["2022-0-00469"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Automat. Contr."],"published-print":{"date-parts":[[2024,7]]},"DOI":"10.1109\/tac.2024.3355326","type":"journal-article","created":{"date-parts":[[2024,1,17]],"date-time":"2024-01-17T18:38:57Z","timestamp":1705516737000},"page":"4765-4772","source":"Crossref","is-referenced-by-count":6,"title":["Final Iteration Convergence Bound of Q-Learning: Switching System Approach"],"prefix":"10.1109","volume":"69","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4962-8478","authenticated-orcid":false,"given":"Donghwan","family":"Lee","sequence":"first","affiliation":[{"name":"Department of Electrical Engineering, KAIST, Daejeon, South Korea"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref3","first-page":"1995","article-title":"Dueling network architectures for deep reinforcement learning","volume-title":"Proc. 33rd Int. Conf. Int. Conf. Mach. Learn.","author":"Wang","year":"2016"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.32657\/10356\/90191"},{"key":"ref5","article-title":"Memory-based control with recurrent neural networks","author":"Heess","year":"2015"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"ref7","first-page":"449","article-title":"A distributional perspective on reinforcement learning","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","author":"Bellemare","year":"2017"},{"key":"ref8","first-page":"1889","article-title":"Trust region policy optimization","volume-title":"Proc. 32nd Int. Conf. Mach. Learn.","author":"Schulman","year":"2015"},{"key":"ref9","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/BF00993306"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21236\/ADA276517"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1137\/S0363012997331639"},{"key":"ref14","first-page":"2613","article-title":"Double Q-learning","volume-title":"Adv. Neural Inf. Process. Syst.","author":"Hasselt","year":"2010"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390240"},{"key":"ref16","first-page":"15556","article-title":"A unified switching system perspective and convergence analysis of Q-learning algorithms","volume-title":"34th Conf. Neural Inf. Process. Syst.","author":"Lee","year":"2020"},{"key":"ref17","first-page":"2232","article-title":"Zap Q-learning","volume-title":"Proc. 31st Int. Conf. Neural Inf. Process. Syst.","author":"Devraj","year":"2017"},{"key":"ref18","first-page":"1064","article-title":"The asymptotic convergence-rate of Q-learning","volume-title":"Adv. Neural Inf. Process. Syst.","author":"Szepesvri","year":"1998"},{"key":"ref19","first-page":"996","article-title":"Finite-sample convergence rates for Q-learning and indirect algorithms","volume-title":"Adv. Neural Inf. Process. Syst.","author":"Kearns","year":"1999"},{"key":"ref20","first-page":"1","article-title":"Learning rates for Q-learning","volume":"5","author":"Even-Dar","year":"2003","journal-title":"J. Mach. Learn. Res."},{"key":"ref21","first-page":"2411","article-title":"Speedy Q-learning","volume-title":"Proc. 24th Int. Conf. Neural Inf. Process. Syst.","author":"Azar","year":"2011"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.sysconle.2012.08.014"},{"key":"ref23","article-title":"Stochastic approximation with cone-contractive operators: Sharp $\\ell _\\infty$-bounds for Q-learning","author":"Wainwright","year":"2019"},{"key":"ref24","article-title":"Finite-time analysis of asynchronous stochastic approximation and Q-learning","volume-title":"Proc. 33rd Ann. Conf. Learn. Theory","author":"Qu","year":"2020"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/tit.2021.3120096"},{"key":"ref26","article-title":"A Lyapunov theory for finite-sample guarantees of asynchronous Q-learning and TD-learning variants","author":"Chen","year":"2021"},{"key":"ref27","first-page":"582","article-title":"Periodic Q-learning","volume-title":"Learning for Dynamics and Control","author":"Lee","year":"2020"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1137\/22m1489976"},{"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\/978-1-4612-0017-8"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2008.2012009"},{"key":"ref32","volume-title":"Linear System Theory and Design","author":"Chen","year":"1995"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-71225-1_5"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/j.sysconle.2005.08.011"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/BF00115009"}],"container-title":["IEEE Transactions on Automatic Control"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9\/10575939\/10402068.pdf?arnumber=10402068","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,2]],"date-time":"2025-01-02T19:48:50Z","timestamp":1735847330000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10402068\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7]]},"references-count":35,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tac.2024.3355326","relation":{},"ISSN":["0018-9286","1558-2523","2334-3303"],"issn-type":[{"value":"0018-9286","type":"print"},{"value":"1558-2523","type":"electronic"},{"value":"2334-3303","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,7]]}}}