{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,7,21]],"date-time":"2024-07-21T00:06:56Z","timestamp":1721520416315},"reference-count":46,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61976243","62033010"],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Science and Technology Development Plan of Henan Province of China","award":["231100220600","231111222600"]},{"name":"Leading Talents of Science and Technology in the Central Plain of China","award":["224200510004"]},{"name":"Scientific and Technological Innovation Teams and Talents of Colleges and Universities in Henan Province of China","award":["24IRTSTHN022","22HASTIT014"]},{"name":"Basic Research Projects in the University of Henan Province of China","award":["23ZX003"]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2021M690914"],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Syst. Man Cybern, Syst."],"published-print":{"date-parts":[[2024,8]]},"DOI":"10.1109\/tsmc.2024.3382986","type":"journal-article","created":{"date-parts":[[2024,4,26]],"date-time":"2024-04-26T18:01:24Z","timestamp":1714154484000},"page":"4630-4641","source":"Crossref","is-referenced-by-count":0,"title":["Decentralized Adaptive TD(\u03bb) Learning With Linear Function Approximation: Nonasymptotic Analysis"],"prefix":"10.1109","volume":"54","author":[{"ORCID":"http:\/\/orcid.org\/0000-0002-6411-7035","authenticated-orcid":false,"given":"Junlong","family":"Zhu","sequence":"first","affiliation":[{"name":"School of Information Engineering, Henan University of Science and Technology, Luoyang, China"}]},{"ORCID":"http:\/\/orcid.org\/0009-0001-5500-7192","authenticated-orcid":false,"given":"Tao","family":"Mao","sequence":"additional","affiliation":[{"name":"School of Information Engineering, Henan University of Science and Technology, Luoyang, China"}]},{"ORCID":"http:\/\/orcid.org\/0000-0002-2523-1089","authenticated-orcid":false,"given":"Mingchuan","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Information Engineering, Henan University of Science and Technology, Luoyang, China"}]},{"ORCID":"http:\/\/orcid.org\/0000-0002-6907-7837","authenticated-orcid":false,"given":"Quanbo","family":"Ge","sequence":"additional","affiliation":[{"name":"School of Automation, Nanjing University of Information Science and Technology, Nanjing, China"}]},{"ORCID":"http:\/\/orcid.org\/0000-0003-1572-5293","authenticated-orcid":false,"given":"Qingtao","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Information Engineering, Henan University of Science and Technology, Luoyang, China"}]},{"ORCID":"http:\/\/orcid.org\/0000-0001-5224-4048","authenticated-orcid":false,"given":"Keqin","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Computer Science, State University of New York, New Paltz, NY, USA"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton","year":"2018"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/BF00115009"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2018.2865505"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.13140\/RG.2.2.18893.74727"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/9.580874"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992701"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1023\/A:1007609817671"},{"key":"ref11","first-page":"8477","article-title":"Characterizing the exact behaviors of temporal difference learning algorithms using Markov jump linear system theory","volume-title":"Proc. 33rd Int. Conf. Neural Inf. Process. Syst. (NeurIPS)","author":"Hu"},{"key":"ref12","first-page":"1","article-title":"Decentralized TD tracking with linear function approximation and its finite-time analysis","volume-title":"Proc. 34th Int. Conf. Neural Inf. Process. Syst. (NeurIPS)","author":"Wang"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1287\/opre.2020.2024"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12079"},{"key":"ref15","first-page":"2803","article-title":"Finite-time error bounds for linear stochastic approximation and TD learning","volume-title":"Proc. 32nd Annu. Conf. Learn. Theory","author":"Srikant"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3119645"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17252"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2021.3128723"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2014.2306253"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2016.2585302"},{"key":"ref21","first-page":"1626","article-title":"Finite-time analysis of distributed TD(0) with linear function approximation for multi-agent reinforcement learning","volume-title":"Proc. 36th Int. Conf. Mach. Learn. (ICML)","author":"Doan"},{"key":"ref22","first-page":"4485","article-title":"Finitetime analysis of decentralized temporal-difference learning with linear function approximation","volume-title":"Proc. 23rd Int. Conf. Artif. Intell. Statist., (AISTATS)","author":"Sun"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2021.3071962"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1137\/20M1311971"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2021.3090952"},{"key":"ref26","first-page":"1","article-title":"Learning rates for Q-learning","volume":"5","author":"Even-Dar","year":"2003","journal-title":"J. Mach. Learn. Res."},{"key":"ref27","first-page":"1","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. 3rd Int. Conf. Learn. Represent. (ICLR)","author":"Kingma"},{"key":"ref28","first-page":"1","article-title":"On the convergence of Adam and beyond","volume-title":"Proc. 6th Int. Conf. Learn. Represent. (ICLR)","author":"Reddi"},{"key":"ref29","first-page":"459","article-title":"Neural Optimizer search with reinforcement learning","volume-title":"Proc. 34th Int. Conf. Mach. Learn. (ICML)","author":"Bello"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.120406"},{"key":"ref31","article-title":"A multistep Lyapunov approach for finite-time analysis of biased stochastic approximation","author":"Wang","year":"2020","journal-title":"arXiv:1909.04299"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1994.6.6.1185"},{"key":"ref33","first-page":"626","article-title":"On TD(0) with function approximation: Concentration bounds and a centered variant with exponential convergence","volume-title":"Proc. 32nd Int. Conf. Mach. Learn. (ICML)","author":"Korda"},{"key":"ref34","volume-title":"Finite Time Bounds for Temporal Difference Learning with Function Approximation: Problems with Some \u2018State-of-the-Art\u2019 Results","author":"Lakshminarayanan","year":"2017"},{"key":"ref35","first-page":"2121","article-title":"Adaptive subgradient methods for online learning and stochastic optimization","volume":"12","author":"Duchi","year":"2011","journal-title":"J. Mach. Learn. Res."},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TCNS.2017.2698261"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1137\/16M1084316"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-020-01487-0"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2021.3097714"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2021.3112691"},{"key":"ref41","article-title":"On the convergence of decentralized adaptive gradient methods","author":"Chen","year":"2021","journal-title":"arXiv:2109.03194"},{"key":"ref42","article-title":"DADAM: A consensus-based distributed adaptive gradient method for online optimization","author":"Nazari","year":"2019","journal-title":"arXiv:1901.09109"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1090\/mbk\/107"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2018.2817461"},{"issue":"51","key":"ref45","first-page":"1","article-title":"Projection-free decentralized online learning for submodular maximization over timevarying networks","volume":"22","author":"Zhu","year":"2021","journal-title":"J. Mach. Learn. Res."},{"key":"ref46","first-page":"6379","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume-title":"Proc. 31st Int. Conf. Neural Inf. Process. Syst. (NIPS)","author":"Lowe"}],"container-title":["IEEE Transactions on Systems, Man, and Cybernetics: Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6221021\/10604660\/10508812.pdf?arnumber=10508812","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,20]],"date-time":"2024-07-20T05:10:45Z","timestamp":1721452245000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10508812\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8]]},"references-count":46,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tsmc.2024.3382986","relation":{},"ISSN":["2168-2216","2168-2232"],"issn-type":[{"value":"2168-2216","type":"print"},{"value":"2168-2232","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,8]]}}}