{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T17:08:10Z","timestamp":1774631290279,"version":"3.50.1"},"reference-count":21,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000183","name":"Army Research Office","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000183","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Control Syst. Lett."],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/lcsys.2023.3287952","type":"journal-article","created":{"date-parts":[[2023,6,20]],"date-time":"2023-06-20T17:36:46Z","timestamp":1687282606000},"page":"2892-2897","source":"Crossref","is-referenced-by-count":7,"title":["Distributed TD(0) With Almost No Communication"],"prefix":"10.1109","volume":"7","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7333-6291","authenticated-orcid":false,"given":"Rui","family":"Liu","sequence":"first","affiliation":[{"name":"Division of Systems Engineering, Boston University, Quincy, MA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5852-9789","authenticated-orcid":false,"given":"Alex","family":"Olshevsky","sequence":"additional","affiliation":[{"name":"Department of ECE, Division of Systems Engineering, Boston University, Boston, MA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2009.2031203"},{"key":"ref12","article-title":"Optimal lockdown for pandemic control","author":"ma","year":"2020","journal-title":"arXiv 2010 12923"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1137\/16M1076629"},{"key":"ref14","article-title":"Approximate temporal difference learning is a gradient descent for reversible policies","author":"ollivier","year":"2018","journal-title":"arXiv 1805 00869"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/9.580874"},{"key":"ref11","first-page":"6905","article-title":"Temporal difference learning as gradient splitting","author":"liu","year":"2021","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref10","article-title":"Distributed TD(0) with almost no communication","author":"liu","year":"2021","journal-title":"arXiv 2104 07855"},{"key":"ref21","first-page":"13762","article-title":"Decentralized TD tracking with linear function approximation and its finite-time analysis","volume":"33","author":"wang","year":"2020","journal-title":"Proc Int Conf Adv Neural Inf Process Syst"},{"key":"ref2","first-page":"1691","article-title":"A finite time analysis of temporal difference learning with linear function approximation","author":"bhandari","year":"2018","journal-title":"Proc Conf Learn Theory"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ISIT.2010.5513273"},{"key":"ref17","first-page":"1","article-title":"Finite-sample analysis of decentralized temporal-difference learning with linear function approximation","author":"sun","year":"2020","journal-title":"Proc Int Conf Artif Intell Stat"},{"key":"ref16","article-title":"Towards understanding asynchronous advantage actor-critic: Convergence and linear speedup","author":"shen","year":"2020","journal-title":"arXiv 2012 15511"},{"key":"ref19","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/BF00115009"},{"key":"ref8","first-page":"10997","article-title":"Federated reinforcement learning: Linear speedup under Markovian sampling","author":"khodadadian","year":"2022","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/SFCS.2003.1238221"},{"key":"ref9","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":"ref4","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":"ref3","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12079"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TAES.2020.2965811"},{"key":"ref5","first-page":"1626","article-title":"Finite-time analysis of distributed TD(0) with linear function approximation on multi-agent reinforcement learning","author":"doan","year":"2019","journal-title":"Proc Int Conf Mach Learn"}],"container-title":["IEEE Control Systems Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7782633\/9828546\/10158355.pdf?arnumber=10158355","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,18]],"date-time":"2023-07-18T20:03:54Z","timestamp":1689710634000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10158355\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/lcsys.2023.3287952","relation":{},"ISSN":["2475-1456"],"issn-type":[{"value":"2475-1456","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}