{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,24]],"date-time":"2026-01-24T15:53:01Z","timestamp":1769269981087,"version":"3.49.0"},"reference-count":52,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["ECCS 1931932"],"award-info":[{"award-number":["ECCS 1931932"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62203073"],"award-info":[{"award-number":["62203073"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["2212582"],"award-info":[{"award-number":["2212582"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["2241585"],"award-info":[{"award-number":["2241585"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Automat. Contr."],"published-print":{"date-parts":[[2024,11]]},"DOI":"10.1109\/tac.2024.3386061","type":"journal-article","created":{"date-parts":[[2024,4,8]],"date-time":"2024-04-08T21:19:28Z","timestamp":1712611168000},"page":"7524-7539","source":"Crossref","is-referenced-by-count":5,"title":["Asynchronous Distributed Reinforcement Learning for LQR Control via Zeroth-Order Block Coordinate Descent"],"prefix":"10.1109","volume":"69","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0066-204X","authenticated-orcid":false,"given":"Gangshan","family":"Jing","sequence":"first","affiliation":[{"name":"Chongqing University, Chongqing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4247-0698","authenticated-orcid":false,"given":"He","family":"Bai","sequence":"additional","affiliation":[{"name":"Oklahoma State University, Stillwater, OK, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8417-5411","authenticated-orcid":false,"given":"Jemin","family":"George","sequence":"additional","affiliation":[{"name":"DEVCOM Army Research Laboratory, Adelphi, MD, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3474-8215","authenticated-orcid":false,"given":"Aranya","family":"Chakrabortty","sequence":"additional","affiliation":[{"name":"North Carolina State University, Raleigh, NC, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8829-9390","authenticated-orcid":false,"given":"Piyush K.","family":"Sharma","sequence":"additional","affiliation":[{"name":"DEVCOM Army Research Laboratory, Adelphi, MD, USA"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1002\/0471722138"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s10208-015-9296-2"},{"key":"ref3","first-page":"385","article-title":"Online convex optimization in the bandit setting: Gradient descent without a gradient","volume-title":"Proc. 16th Annu. ACM-SIAM Symp. Discrete Algorithms","author":"Flaxman","year":"2005"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3128572.3140448"},{"key":"ref5","first-page":"1467","article-title":"Global convergence of policy gradient methods for the linear quadratic regulator","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Fazel","year":"2018"},{"issue":"21","key":"ref6","first-page":"1","article-title":"Derivative-free methods for policy optimization: Guarantees for linear quadratic systems","volume":"21","author":"Malik","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref7","first-page":"287","article-title":"Learning the globally optimal distributed LQ regulator","volume-title":"Proc. Learn. Dyn. Control","author":"Furieri","year":"2020"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/LCSYS.2020.3006256"},{"key":"ref9","first-page":"28","article-title":"Optimal algorithms for online convex optimization with multi-point bandit feedback","volume-title":"Proc. Conf. Learn. Theory","author":"Agarwal","year":"2010"},{"issue":"1","key":"ref10","first-page":"1703","article-title":"An optimal algorithm for bandit and zero-order convex optimization with two-point feedback","volume":"18","author":"Shamir","year":"2017","journal-title":"J. Mach. Learn. Res."},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2021.110006"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1117\/12.2585808"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2019.2943230"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2019.2896025"},{"key":"ref15","article-title":"Privacy-preserving distributed zeroth-order optimization","author":"Gratton","year":"2020"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TCNS.2020.3024321"},{"key":"ref17","first-page":"10209","article-title":"Distributed zero-order optimization under adversarial noise","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Akhavan","year":"2021"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2021.3128592"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1137\/100802001"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.4310\/AMSA.2016.v1.n1.a2"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1110\/ps.0242703"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-012-0614-z"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-015-0892-3"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s10915-017-0376-0"},{"key":"ref25","first-page":"1193","article-title":"A zeroth-order block coordinate descent algorithm for huge-scale black-box optimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Cai","year":"2021"},{"key":"ref26","article-title":"Zeroth-order stochastic block coordinate type methods for nonconvex optimization","author":"Yu","year":"2019"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2014.10.022"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2020.3012630"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-93818-9_9"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2021.3111853"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2021.3115430"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.23919\/ACC.2019.8814952"},{"key":"ref33","article-title":"On topological and metrical properties of stabilizing feedback gains: The MIMO case","author":"Bu","year":"2019"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2008.925826"},{"key":"ref35","article-title":"LQR through the lens of first order methods: Discrete-time case","author":"Bu","year":"2019"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/LCSYS.2021.3072007"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TCNS.2021.3074256"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/OJCSYS.2022.3171787"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CDC45484.2021.9683331"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3579452"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2013.2241057"},{"key":"ref42","first-page":"2681","article-title":"Deep decentralized multi-task multi-agent reinforcement learning under partial observability","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Omidshafiei","year":"2017"},{"key":"ref43","first-page":"6382","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume-title":"Proc. 31st Int. Conf. Neural Inf. Process. Syst.","author":"Lowe","year":"2017"},{"key":"ref44","first-page":"5872","article-title":"Fully decentralized multi-agent reinforcement learning with networked agents","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhang","year":"2018"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TCNS.2021.3078100"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1214\/ECP.v18-2865"},{"key":"ref47","volume-title":"Social Networks: Models of Information Influence, Control and Confrontation","volume":"189","author":"Chkhartishvili","year":"2018"},{"key":"ref48","article-title":"Multi-agent systems with reciprocal interaction laws","author":"Chen","year":"2014"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2016.2636810"},{"key":"ref50","article-title":"Asynchronous distributed reinforcement learning for LQR control via zeroth-order block coordinate descent","author":"Jing","year":"2021"},{"key":"ref51","first-page":"256","article-title":"Scalable reinforcement learning of localized policies for multi-agent networked systems","volume-title":"Proc. Learn. Dyn. Control","author":"Qu","year":"2020"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CDC42340.2020.9304202"}],"container-title":["IEEE Transactions on Automatic Control"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/9\/10736196\/10494371-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9\/10736196\/10494371.pdf?arnumber=10494371","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,2]],"date-time":"2025-01-02T19:48:39Z","timestamp":1735847319000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10494371\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11]]},"references-count":52,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/tac.2024.3386061","relation":{},"ISSN":["0018-9286","1558-2523","2334-3303"],"issn-type":[{"value":"0018-9286","type":"print"},{"value":"1558-2523","type":"electronic"},{"value":"2334-3303","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11]]}}}