{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T17:05:45Z","timestamp":1774631145130,"version":"3.50.1"},"reference-count":23,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2025,2,1]],"date-time":"2025-02-01T00:00:00Z","timestamp":1738368000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,2,1]],"date-time":"2025-02-01T00:00:00Z","timestamp":1738368000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,2,1]],"date-time":"2025-02-01T00:00:00Z","timestamp":1738368000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Automat. Contr."],"published-print":{"date-parts":[[2025,2]]},"DOI":"10.1109\/tac.2024.3469328","type":"journal-article","created":{"date-parts":[[2024,9,27]],"date-time":"2024-09-27T14:40:05Z","timestamp":1727448005000},"page":"1388-1394","source":"Crossref","is-referenced-by-count":2,"title":["A Simple Finite-Time Analysis of TD Learning With Linear Function Approximation"],"prefix":"10.1109","volume":"70","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-4590-553X","authenticated-orcid":false,"given":"Aritra","family":"Mitra","sequence":"first","affiliation":[{"name":"Department of Electrical and Computer Engineering, North Carolina State University, Raleigh, NC, USA"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/BF00115009"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/9.580874"},{"key":"ref3","volume-title":"Stochastic Approximation: A Dynamical Systems Viewpoint","volume":"48","author":"Borkar","year":"2009"},{"key":"ref4","first-page":"626","article-title":"On TD(0) with function approximation: Concentration bounds and a centered variant with exponential convergence","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Korda","year":"2015"},{"key":"ref5","article-title":"Finite time bounds for temporal difference learning with function approximation: Problems with some state-of-the-art results","author":"Narayanan","year":"2017"},{"key":"ref6","first-page":"1347","article-title":"Linear stochastic approximation: Constant step-size and iterate averaging","volume-title":"Proc. 20st Int. Conf. Artif. Intell. Statist.","author":"Lakshminarayanan","year":"2018"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12079"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1287\/opre.2020.2024"},{"key":"ref9","first-page":"2803","article-title":"Finite-time error bounds for linear stochastic approximation and TD learning","volume-title":"Proc. Conf. Learn. Theory","author":"Srikant","year":"2019"},{"key":"ref10","first-page":"111","article-title":"A tight convergence analysis for stochastic gradient descent with delayed updates","volume-title":"Proc. Int. Conf. Algorithmic Learn. Theory","author":"Arjevani","year":"2020"},{"key":"ref11","article-title":"On communication compression for distributed optimization on heterogeneous data","author":"Stich","year":"2020"},{"key":"ref12","first-page":"2746","article-title":"Stochastic approximation with delayed updates: Finite-time rates under Markovian sampling","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Adibi","year":"2024"},{"key":"ref13","first-page":"331","article-title":"Markov decision processes","volume-title":"Handbooks in Operations Research and Management Science","volume":"2","author":"Puterman","year":"1990"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1090\/mbk\/107"},{"key":"ref15","article-title":"Performance of Q-learning with linear function approximation: Stability and finite-time analysis","author":"Chen","year":"2019"},{"key":"ref16","article-title":"Temporal difference learning with compressed updates: Error-feedback meets reinforcement learning","volume-title":"Trans. Mach. Learn. Res.","author":"Mitra","year":"2024"},{"key":"ref17","article-title":"The ODE method for asymptotic statistics in stochastic approximation and reinforcement learning","author":"Borkar","year":"2021"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3578338.3593526"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CDC49753.2023.10383986"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.sysconle.2005.08.011"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.sysconle.2012.08.014"},{"key":"ref22","first-page":"3185","article-title":"Finite-time analysis of asynchronous stochastic approximation and Q-learning","volume-title":"Proc. Int. Conf. Learn. Theory","author":"Qu","year":"2020"},{"key":"ref23","article-title":"On the performance of temporal difference learning with neural networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Tian","year":"2023"}],"container-title":["IEEE Transactions on Automatic Control"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/9\/10857662\/10697283.pdf?arnumber=10697283","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,30]],"date-time":"2026-01-30T21:06:54Z","timestamp":1769807214000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10697283\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2]]},"references-count":23,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tac.2024.3469328","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":[[2025,2]]}}}