{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T15:12:01Z","timestamp":1774969921505,"version":"3.50.1"},"reference-count":62,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE J. Sel. Areas Inf. Theory"],"published-print":{"date-parts":[[2021,6]]},"DOI":"10.1109\/jsait.2021.3078754","type":"journal-article","created":{"date-parts":[[2021,5,19]],"date-time":"2021-05-19T21:14:38Z","timestamp":1621458878000},"page":"652-664","source":"Crossref","is-referenced-by-count":32,"title":["On Finite-Time Convergence of Actor-Critic Algorithm"],"prefix":"10.1109","volume":"2","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9651-1061","authenticated-orcid":false,"given":"Shuang","family":"Qiu","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5269-9958","authenticated-orcid":false,"given":"Zhuoran","family":"Yang","sequence":"additional","affiliation":[]},{"given":"Jieping","family":"Ye","sequence":"additional","affiliation":[]},{"given":"Zhaoran","family":"Wang","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","first-page":"6144","article-title":"Finite sample analyses for TD(0) with function approximation","volume":"32","author":"dalal","year":"2018","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/BF00114723"},{"key":"ref33","author":"zhang","year":"2018","journal-title":"Finite-sample analysis for decentralized batch multi-agent reinforcement learning with networked agents"},{"key":"ref32","first-page":"367","article-title":"A convergent online single time scale actor critic algorithm","volume":"11","author":"castro","year":"2010","journal-title":"J Mach Learn Res"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.sysconle.2010.08.013"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2009.07.008"},{"key":"ref37","first-page":"49","article-title":"Least-squares temporal difference learning","author":"boyan","year":"1999","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-27645-3_2"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2018.8619440"},{"key":"ref34","author":"chen","year":"2018","journal-title":"Communication-efficient policy gradient methods for distributed reinforcement learning"},{"key":"ref60","first-page":"1199","article-title":"Finite sample analysis of two-timescale stochastic approximation with applications to reinforcement learning","author":"dalal","year":"2018","journal-title":"Proc Conf Learn Theory"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5779"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.11251"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2007.11.026"},{"key":"ref27","first-page":"1531","article-title":"A natural policy gradient","author":"kakade","year":"2002","journal-title":"Advances in neural information processing systems"},{"key":"ref29","first-page":"105","article-title":"Incremental natural actor-critic algorithms","author":"bhatnagar","year":"2007","journal-title":"Advances in neural information processing systems"},{"key":"ref2","author":"goodfellow","year":"2016","journal-title":"Deep Learning"},{"key":"ref1","article-title":"On the finite-time convergence of actor-critic algorithm","author":"qiu","year":"2019","journal-title":"Proc Optim Found Reinforcement Learn Workshop Adv Neural Inf Process Syst (NeurIPS)"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s10479-007-0176-2"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1038\/sj.jors.2600425"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2017.2712906"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/BF00114727"},{"key":"ref23","volume":"64","author":"chen","year":"2006","journal-title":"Stochastic Approximation and Its Applications"},{"key":"ref26","first-page":"1691","article-title":"A finite time analysis of temporal difference learning with linear function approximation","author":"bhandari","year":"2018","journal-title":"Proc 31st Conf Learn Theory"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/S0005-1098(99)00099-0"},{"key":"ref50","author":"hong","year":"2020","journal-title":"A two-timescale framework for bilevel optimization Complexity analysis and application to actor-critic"},{"key":"ref51","author":"fu","year":"2020","journal-title":"Single-timescale actor-critic provably finds globally optimal policy"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553501"},{"key":"ref58","article-title":"A convergent O(n) temporal-difference algorithm for off-policy learning with linear function approximation","author":"sutton","year":"2008","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1090\/mbk\/107"},{"key":"ref56","volume":"169","author":"bhatia","year":"2013","journal-title":"Matrix Analysis"},{"key":"ref55","article-title":"Convergent reinforcement learning with function approximation: A bilevel optimization perspective","author":"yang","year":"2018","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref54","article-title":"Gradient temporal-difference learning algorithms","author":"maei","year":"2011"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/9.580874"},{"key":"ref52","article-title":"Analysis of some incremental variants of policy iteration: First steps toward understanding actor-critic learning systems","author":"williams","year":"1993"},{"key":"ref10","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","author":"sutton","year":"2000","journal-title":"Advances in neural information processing systems"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/BF00115009"},{"key":"ref40","author":"srikant","year":"2019","journal-title":"Finite-time error bounds for linear stochastic approximation and TD learning"},{"key":"ref12","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref13","first-page":"387","article-title":"Deterministic policy gradient algorithms","author":"silver","year":"2014","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref14","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2016","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-93-86279-38-5"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1137\/S0363012997331639"},{"key":"ref17","author":"kushner","year":"2003","journal-title":"Stochastic Approximation and Recursive Algorithms and Applications"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/BF02592948"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1137\/0913069"},{"key":"ref4","first-page":"1889","article-title":"Trust region policy optimization","author":"schulman","year":"2015","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref3","first-page":"1008","article-title":"Actor-critic algorithms","author":"konda","year":"2000","journal-title":"Advances in neural information processing systems"},{"key":"ref6","doi-asserted-by":"crossref","first-page":"484","DOI":"10.1038\/nature16961","article-title":"Mastering the game of Go with deep neural networks and tree search","volume":"529","author":"silver","year":"2016","journal-title":"Nature"},{"key":"ref5","author":"schulman","year":"2017","journal-title":"Proximal policy optimization algorithms"},{"key":"ref8","year":"2018","journal-title":"Openai five"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"key":"ref49","author":"xu","year":"2020","journal-title":"Improving sample complexity bounds for (natural) actor-critic algorithms"},{"key":"ref9","author":"vinyals","year":"2019","journal-title":"Alphastar Mastering the real-time strategy game StarCraft II"},{"key":"ref46","first-page":"809","article-title":"Policy evaluation with temporal differences: A survey and comparison","volume":"15","author":"dann","year":"2014","journal-title":"J Mach Learn Res"},{"key":"ref45","first-page":"4962","article-title":"Convergent tree backup and retrace with function approximation","author":"touati","year":"2018","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref48","author":"wu","year":"2020","journal-title":"A finite time analysis of two time-scale actor critic methods"},{"key":"ref47","author":"kumar","year":"2019","journal-title":"On the sample complexity of actor-critic method for reinforcement learning with function approximation"},{"key":"ref42","first-page":"504","article-title":"Finite-sample analysis of proximal gradient TD algorithms","author":"liu","year":"2015","journal-title":"Proc Conf Uncertainty of Artificial Intelligence"},{"key":"ref41","author":"zou","year":"2019","journal-title":"Finite-sample analysis for SARSA with linear function approximation"},{"key":"ref44","first-page":"5504","article-title":"Finite sample analysis of the GTD policy evaluation algorithms in Markov setting","author":"wang","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref43","first-page":"1049","article-title":"Stochastic variance reduction methods for policy evaluation","author":"du","year":"2017","journal-title":"Proc 34th Int Conf Mach Learn Vol 70"}],"container-title":["IEEE Journal on Selected Areas in Information Theory"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8700143\/9459757\/09435807.pdf?arnumber=9435807","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,11,8]],"date-time":"2021-11-08T22:36:44Z","timestamp":1636411004000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9435807\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6]]},"references-count":62,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/jsait.2021.3078754","relation":{},"ISSN":["2641-8770"],"issn-type":[{"value":"2641-8770","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,6]]}}}