{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T06:31:35Z","timestamp":1790749895992,"version":"4.1.0"},"reference-count":41,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2023,4,1]],"date-time":"2023-04-01T00:00:00Z","timestamp":1680307200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,4,1]],"date-time":"2023-04-01T00:00:00Z","timestamp":1680307200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,4,1]],"date-time":"2023-04-01T00:00:00Z","timestamp":1680307200000},"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":[[2023,4]]},"DOI":"10.1109\/tac.2022.3172593","type":"journal-article","created":{"date-parts":[[2022,5,5]],"date-time":"2022-05-05T19:48:20Z","timestamp":1651780100000},"page":"2140-2153","source":"Crossref","is-referenced-by-count":10,"title":["Finite-Time Analysis of Markov Gradient Descent"],"prefix":"10.1109","volume":"68","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5135-3429","authenticated-orcid":false,"given":"Thinh T.","family":"Doan","sequence":"first","affiliation":[{"name":"Bradley Department of Electrical and Computer Engineering, Virginia Tech, Blacksburg, VA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177729586"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2015.03.018"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/72.248467"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/BF01211655"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2003.821649"},{"key":"ref6","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton","year":"2018"},{"key":"ref7","volume-title":"Neuro-Dynamic Programming","author":"Bertsekas","year":"1999"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-84858-7"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1137\/16M1080173"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2011.09.043"},{"key":"ref11","volume-title":"Lectures on Optimization Methods for Machine Learning","author":"Lan","year":"2020"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/0005-1098(80)90086-2"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.sysconle.2004.08.007"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1137\/s0363012901385691"},{"key":"ref15","article-title":"Approximate temporal difference learning is a gradient descent for reversible policies","author":"Ollivier","year":"2018"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1137\/080726380"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1137\/08073038X"},{"issue":"12","key":"ref18","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1020281327116","article-title":"An introduction to MCMC for machine learning","volume":"50","author":"Andrieu","year":"2003","journal-title":"Mach. Learn."},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1137\/110836043"},{"key":"ref20","first-page":"9918","article-title":"On Markov chain gradient descent","volume-title":"Proc. 32nd Int. Conf. Neural Inf. Process. Syst.","author":"Sun","year":"2018"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-93-86279-38-5"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-75894-2"},{"key":"ref23","article-title":"Convergence rates of accelerated Markov gradient descent with applications in reinforcement learning","author":"Doan","year":"2020"},{"key":"ref24","first-page":"1691","article-title":"A finite time analysis of temporal difference learning with linear function approximation","volume-title":"Proc. 31st Conf. Learn. Theory, Ser. Mach. Learn. Res.","volume":"75","author":"Bhandari","year":"2018"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/9.580874"},{"key":"ref26","first-page":"1","article-title":"Finite-time error bounds for linear stochastic approximation and TD learning","volume-title":"Proc. 32nd Annu. Conf. Learn. Theory","author":"Srikant","year":"2019"},{"key":"ref27","article-title":"Performance of Q-learning with linear function approximation: Stability and finite-time analysis","author":"Chen","year":"2019"},{"key":"ref28","first-page":"1944","article-title":"Non-asymptotic analysis of biased stochastic approximation scheme","volume-title":"Proc. Conf. Learn. Theory","author":"Karimi","year":"2019"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1090\/mbk\/058"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1137\/070704277"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46128-1_50"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-016-1091-6"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/BF02096261"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/s11590-016-1058-9"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1137\/140992990"},{"key":"ref37","first-page":"64","article-title":"Optimality and approximation with policy gradient methods in Markov decision processes","volume-title":"Proc. 33rd Conf. Mach. Learn. Res.","volume":"125","author":"Agarwal","year":"2020"},{"key":"ref38","article-title":"Optimizing static linear feedback: Gradient method","author":"Fatkhullin","year":"2020"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1017\/S0266466602181023"},{"issue":"2","key":"ref40","first-page":"219","article-title":"Proprits de mlange des processus autorgressifs polynomiaux","volume-title":"Annales De LI. H. P. Probabilits et Statistiques","volume":"26","author":"Mokkadem","year":"1990"},{"key":"ref41","article-title":"Finite-time analysis and restarting scheme for linear two-time-scale stochastic approximation","author":"Doan","year":"2019"}],"container-title":["IEEE Transactions on Automatic Control"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9\/10084346\/09769873.pdf?arnumber=9769873","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,22]],"date-time":"2024-01-22T23:03:31Z","timestamp":1705964611000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9769873\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,4]]},"references-count":41,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tac.2022.3172593","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":[[2023,4]]}}}