{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,22]],"date-time":"2025-12-22T14:43:47Z","timestamp":1766414627858,"version":"3.37.3"},"reference-count":28,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"NSF","doi-asserted-by":"publisher","award":["CIF-1944993","2112533"],"award-info":[{"award-number":["CIF-1944993","2112533"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Control Syst. Lett."],"published-print":{"date-parts":[[2022]]},"DOI":"10.1109\/lcsys.2022.3172242","type":"journal-article","created":{"date-parts":[[2022,5,3]],"date-time":"2022-05-03T20:17:20Z","timestamp":1651609040000},"page":"2611-2616","source":"Crossref","is-referenced-by-count":8,"title":["Finite-Sample Analysis of Off-Policy Natural Actor\u2013Critic With Linear Function Approximation"],"prefix":"10.1109","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9915-5595","authenticated-orcid":false,"given":"Zaiwei","family":"Chen","sequence":"first","affiliation":[{"name":"School of Industrial and Systems Engineering, Georgia Institute of Technology, Atlanta, GA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5197-4652","authenticated-orcid":false,"given":"Sajad","family":"Khodadadian","sequence":"additional","affiliation":[{"name":"School of Industrial and Systems Engineering, Georgia Institute of Technology, Atlanta, GA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5797-1639","authenticated-orcid":false,"given":"Siva Theja","family":"Maguluri","sequence":"additional","affiliation":[{"name":"School of Industrial and Systems Engineering, Georgia Institute of Technology, Atlanta, GA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2009.07.008"},{"key":"ref11","first-page":"11581","article-title":"Doubly robust off-policy actor-critic: Convergence and optimality","author":"xu","year":"2021","journal-title":"Proc ICML"},{"key":"ref12","article-title":"Finite-sample analysis of off-policy natural actor-critic with linear function approximation","author":"chen","year":"2021","journal-title":"arXiv 2105 12540"},{"key":"ref13","article-title":"Policy gradient methods for reinforcement learning with function approximation","author":"sutton","year":"1999","journal-title":"Advances in Neural IInformation Processing Systems"},{"key":"ref14","article-title":"A natural policy gradient","author":"kakade","year":"2001","journal-title":"Advances in Neural IInformation Processing Systems"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-022-01816-5"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/9.580874"},{"key":"ref17","first-page":"1","article-title":"Finite-time error bounds for linear stochastic approximation and TD learning","author":"srikant","year":"2019","journal-title":"Proc COLT"},{"key":"ref18","article-title":"A convergent $\\mathcal {O}(n)$\n algorithm for off-policy temporal-difference learning with linear function approximation","author":"sutton","year":"2008","journal-title":"Advances in Neural IInformation Processing Systems"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553501"},{"key":"ref28","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":"ref4","article-title":"Actor-critic algorithms","author":"konda","year":"2000","journal-title":"Advances in Neural IInformation Processing Systems"},{"key":"ref27","first-page":"17617","article-title":"A finite-time analysis of two time-scale actor-critic methods","volume":"33","author":"wu","year":"2020","journal-title":"Proc Int Conf Adv Neural Inf Process Syst"},{"key":"ref3","first-page":"5420","article-title":"Finite-sample analysis of off-policy natural actor-critic algorithm","author":"khodadadian","year":"2021","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref6","first-page":"1","article-title":"On the finite-time convergence of actor-critic algorithm","author":"qiu","year":"2019","journal-title":"Proc NeurIPS Workshop Optim Found Reinforcement Learn"},{"key":"ref5","first-page":"1","article-title":"Neural policy gradient methods: Global optimality and rates of convergence","author":"wang","year":"2019","journal-title":"Proc ICLR"},{"key":"ref8","article-title":"Convergent actor-critic algorithms under off-policy training and function approximation","author":"maei","year":"2018","journal-title":"arXiv 1802 07842"},{"key":"ref7","article-title":"On the sample complexity of actor-critic method for reinforcement learning with function approximation","author":"kumar","year":"2019","journal-title":"arXiv 1910 08412"},{"key":"ref2","first-page":"1","article-title":"On the theory of policy gradient methods: Optimality, approximation, and distribution shift","volume":"22","author":"agarwal","year":"2021","journal-title":"J Mach Learn Res"},{"key":"ref9","first-page":"11204","article-title":"Provably convergent two-timescale off-policy actor-critic with function approximation","author":"zhang","year":"2020","journal-title":"Proc ICML"},{"journal-title":"Reinforcement Learning An Introduction","year":"2018","author":"sutton","key":"ref1"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1137\/S036301299731669X"},{"key":"ref22","first-page":"179","article-title":"Off-policy actor-critic","author":"degris","year":"2012","journal-title":"Proc ICML"},{"key":"ref21","article-title":"Finite sample analysis of two-time-scale natural actor-critic algorithm","author":"khodadadian","year":"2021","journal-title":"arXiv 2101 10506"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.cam.2008.07.037"},{"journal-title":"Neuro-Dynamic Programming","year":"1996","author":"bertsekas","key":"ref23"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1090\/mbk\/107"},{"key":"ref25","first-page":"2603","article-title":"An emphatic approach to the problem of off-policy temporal-difference learning","volume":"17","author":"sutton","year":"2016","journal-title":"J Mach Learn Res"}],"container-title":["IEEE Control Systems Letters"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/7782633\/9462165\/9766396-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7782633\/9462165\/09766396.pdf?arnumber=9766396","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,5]],"date-time":"2022-12-05T22:38:09Z","timestamp":1670279889000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9766396\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/lcsys.2022.3172242","relation":{},"ISSN":["2475-1456"],"issn-type":[{"type":"electronic","value":"2475-1456"}],"subject":[],"published":{"date-parts":[[2022]]}}}