{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,13]],"date-time":"2026-02-13T23:36:32Z","timestamp":1771025792059,"version":"3.50.1"},"reference-count":35,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"NSFC at University of Science and Technology Beijing","award":["12401332"],"award-info":[{"award-number":["12401332"]}]},{"DOI":"10.13039\/501100001809","name":"NSFC at CityU Shenzhen Research Institute","doi-asserted-by":"publisher","award":["12371297"],"award-info":[{"award-number":["12371297"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"NSF of Jiangxi Province","award":["20223BCJ25017"],"award-info":[{"award-number":["20223BCJ25017"]}]},{"name":"Hong Kong RGC General Research Fund","award":["11300424"],"award-info":[{"award-number":["11300424"]}]},{"name":"Hong Kong RGC General Research Fund","award":["11300721"],"award-info":[{"award-number":["11300721"]}]},{"name":"Hong Kong RGC General Research Fund","award":["11311822"],"award-info":[{"award-number":["11311822"]}]},{"name":"CityU Internal","award":["7006014"],"award-info":[{"award-number":["7006014"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2025,6]]},"DOI":"10.1109\/tnnls.2024.3453036","type":"journal-article","created":{"date-parts":[[2024,9,17]],"date-time":"2024-09-17T18:52:01Z","timestamp":1726599121000},"page":"10371-10380","source":"Crossref","is-referenced-by-count":3,"title":["Kernel-Based Decentralized Policy Evaluation for Reinforcement Learning"],"prefix":"10.1109","volume":"36","author":[{"given":"Jiamin","family":"Liu","sequence":"first","affiliation":[{"name":"School of Mathematics and Physics, University of Science and Technology Beijing, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6008-6614","authenticated-orcid":false,"given":"Heng","family":"Lian","sequence":"additional","affiliation":[{"name":"City University of Hong Kong Shenzhen Research Institute, Shenzhen, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2016.7471613"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s10846-017-0468-y"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_36"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3098985"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3087733"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3107375"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2023.3274908"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3207346"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3184956"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3175917"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3213566"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2024.3397704"},{"key":"ref13","first-page":"1563","article-title":"Near-optimal regret bounds for reinforcement learning","volume":"11","author":"Jaksch","year":"2010","journal-title":"J. Mach. Learn. Res."},{"key":"ref14","first-page":"263","article-title":"Minimax regret bounds for reinforcement learning","volume-title":"Proc. 34th. Int. Conf. Mach. Learn.","author":"Azar"},{"key":"ref15","first-page":"1","article-title":"Is Q-learning provably efficient?","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Jin"},{"key":"ref16","first-page":"1","article-title":"Worst-case regret bounds for exploration via randomized value functions","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Russo"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/tit.2021.3120096"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/BF00115009"},{"key":"ref19","first-page":"1","article-title":"Finite-time performance bounds and adaptive learning rate selection for two time-scale reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Gupta"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1287\/opre.2020.2024"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12079"},{"key":"ref22","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.","author":"Doan"},{"key":"ref23","first-page":"4485","article-title":"Finite-time analysis of decentralized temporal-difference learning with linear function approximation","volume-title":"Proc. 23rd Int. Conf. Artif. Intell. Statist.","author":"Sun"},{"key":"ref24","first-page":"1","article-title":"Fitted Q-iteration in continuous action-space MDPs","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Antos"},{"issue":"20","key":"ref25","first-page":"1","article-title":"Convergences of regularized algorithms and stochastic gradient methods with random projections","volume":"21","author":"Lin","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1090\/s0002-9947-1950-0051437-7"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611970128"},{"key":"ref28","first-page":"1","article-title":"Using the Nystr\u00f6m method to speed up kernel machines","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Williams"},{"key":"ref29","first-page":"2153","article-title":"On the Nystr\u00f6m method for approximating a Gram matrix for improved kernel-based learning","volume":"6","author":"Drineas","year":"2005","journal-title":"J. Mach. Learn. Res."},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1137\/130943170"},{"key":"ref31","first-page":"1","article-title":"Can decentralized algorithms outperform centralized algorithms? A case study for decentralized parallel stochastic gradient descent","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lian"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.3166\/EJC.18.539-557"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2014.2364096"},{"key":"ref34","article-title":"Multi-goal reinforcement learning: Challenging robotics environments and request for research","author":"Plappert","year":"2018","journal-title":"arXiv:1802.09464"},{"key":"ref35","first-page":"2186","article-title":"The StarCraft multi-agent challenge","volume-title":"Proc. Int. Conf. Auton. Agents Multiagent Syst. (AAMAS)","author":"Samvelyan"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/5962385\/11022714\/10682059.pdf?arnumber=10682059","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,4]],"date-time":"2025-06-04T17:57:54Z","timestamp":1749059874000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10682059\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6]]},"references-count":35,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2024.3453036","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6]]}}}