{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T05:45:55Z","timestamp":1761975955270,"version":"3.37.3"},"reference-count":48,"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":"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":[{"name":"National Key R&D Program of China","award":["2021YFB1714800"],"award-info":[{"award-number":["2021YFB1714800"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62173034","61925303","62088101"],"award-info":[{"award-number":["62173034","61925303","62088101"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005230","name":"Natural Science Foundation of Chongqing","doi-asserted-by":"publisher","award":["2021ZX4100027"],"award-info":[{"award-number":["2021ZX4100027"]}],"id":[{"id":"10.13039\/501100005230","id-type":"DOI","asserted-by":"publisher"}]},{"name":"CAAI-Huawei MindSpore Open Fund"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Signal Process."],"published-print":{"date-parts":[[2022]]},"DOI":"10.1109\/tsp.2021.3128723","type":"journal-article","created":{"date-parts":[[2021,11,17]],"date-time":"2021-11-17T22:34:15Z","timestamp":1637188455000},"page":"950-962","source":"Crossref","is-referenced-by-count":4,"title":["Finite-Time Error Bounds of Biased Stochastic Approximation With Application to TD-Learning"],"prefix":"10.1109","volume":"70","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7266-2412","authenticated-orcid":false,"given":"Gang","family":"Wang","sequence":"first","affiliation":[{"name":"State Key Lab of Intelligent Control and Decision of Complex Systems and the School of Automation, Beijing Institute of Technology, Beijing, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-377-6.50013-X"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.1995.478953"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1287\/opre.2015.1408"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1287\/opre.2020.2024"},{"key":"ref5","first-page":"1204","article-title":"Convergent temporal-difference learning with arbitrary smooth function approximation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Bhatnagar","year":"2009"},{"article-title":"Lyapunov theory for discrete time systems","year":"2018","author":"Bof","key":"ref6"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s12045-013-0136-x"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1287\/stsy.2022.0097"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2022.110623"},{"key":"ref10","first-page":"1125","article-title":"SBEED: Convergent reinforcement learning with nonlinear function approximation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Dai","year":"2018"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12079"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1017\/9781108591034"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s11134-018-9591-0"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-020-3027-0"},{"key":"ref15","first-page":"8477","article-title":"Characterizing the exact behaviors of temporal difference learning algorithms using Markov jump linear system theory","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Hu","year":"2019"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21236\/ADA276517"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1214\/aoap\/1015961162"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1214\/10-AOP541"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-023-06303-2"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1090\/mbk\/107"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/LCSYS.2023.3287952"},{"article-title":"Greedy-GQ with variance reduction: Finite-time analysis and improved complexity","year":"2021","author":"Ma","key":"ref22"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1017\/cbo9780511626630"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2021.07.007"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2019.2910948"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3001602"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2020.3001054"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177729586"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2019.2936193"},{"key":"ref31","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":"ref32","first-page":"4485","article-title":"Finite-time analysis of decentralized temporal-difference learning with linear function approximation","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Sun","year":"2020"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.comnet.2020.107230"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3449822"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3119645"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/bf00115009"},{"volume-title":"Reinforcement Learning: An Introduction","year":"2018","author":"Sutton","key":"ref37"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/9.580874"},{"key":"ref39","first-page":"10 431","article-title":"Provably efficient neural GTD for off-policy learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Wai","year":"2020"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2019.2904921"},{"article-title":"Finite-sample analysis for two time-scale non-linear TDC with general smooth function approximation","year":"2021","author":"Wang","key":"ref41"},{"key":"ref42","first-page":"555","article-title":"A finite-time analysis of Q-learning with neural network function approximation","volume-title":"Proc. Int. Conf. Mach. Learn","volume":"10","author":"Xu","year":"2020"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2019.2951769"},{"article-title":"Learning to coordinate in multi-agent systems: A coordinated actor-critic algorithm and finite-time guarantees","year":"2021","author":"Zeng","key":"ref44"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2018.2847603"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-018-9820-3"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-019-2751-4"},{"key":"ref48","first-page":"8665","article-title":"Finite-sample analysis for SARSA and Q-learning with linear function approximation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zou","year":"2019"}],"container-title":["IEEE Transactions on Signal Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/78\/9675017\/09618838.pdf?arnumber=9618838","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,12]],"date-time":"2024-01-12T02:25:54Z","timestamp":1705026354000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9618838\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":48,"URL":"https:\/\/doi.org\/10.1109\/tsp.2021.3128723","relation":{},"ISSN":["1053-587X","1941-0476"],"issn-type":[{"type":"print","value":"1053-587X"},{"type":"electronic","value":"1941-0476"}],"subject":[],"published":{"date-parts":[[2022]]}}}