{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,20]],"date-time":"2026-06-20T03:21:21Z","timestamp":1781925681331,"version":"3.54.5"},"reference-count":31,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Fundamental Research Funds for the Central Universities and the Talent Fund of Beijing Jiaotong University"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE J. Sel. Top. Signal Process."],"published-print":{"date-parts":[[2024,10]]},"DOI":"10.1109\/jstsp.2024.3513692","type":"journal-article","created":{"date-parts":[[2024,12,17]],"date-time":"2024-12-17T19:16:18Z","timestamp":1734462978000},"page":"1210-1221","source":"Crossref","is-referenced-by-count":13,"title":["Federated Reinforcement Learning for Resource Allocation in V2X Networks"],"prefix":"10.1109","volume":"18","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0719-3912","authenticated-orcid":false,"given":"Kaidi","family":"Xu","sequence":"first","affiliation":[{"name":"ITP Lab, Department of EEE, Imperial College London, London, U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2843-1614","authenticated-orcid":false,"given":"Shenglong","family":"Zhou","sequence":"additional","affiliation":[{"name":"School of Mathematics and Statistics, Beijing Jiaotong University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7894-2415","authenticated-orcid":false,"given":"Geoffrey Ye","family":"Li","sequence":"additional","affiliation":[{"name":"ITP Lab, Department of EEE, Imperial College London, London, U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/VTC2024-Spring62846.2024.10683304"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2018.1700467"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2018.2833427"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.3019322"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2019.2931583"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/GLOCOMW.2016.7848885"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/LWC.2017.2702747"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2017.2699194"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2018.2827958"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2018.2816942"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2019.2897134"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2019.2933962"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/GLOBECOM42002.2020.9322537"},{"key":"ref14","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","volume-title":"Proc. 12th Int. Conf. Neural Inf. Process. Syst.","author":"Sutton","year":"1999"},{"key":"ref15","first-page":"387","article-title":"Deterministic policy gradient algorithms","volume-title":"Proc. Int. Conf. Mach. Learn","author":"Silver","year":"2014"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2952411"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2023.3275632"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/GLOCOM.2018.8647927"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.20517\/ir.2021.02"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2021.3131534"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2022.3173057"},{"key":"ref22","first-page":"1273","article-title":"Communication-efficient learning of deep networks from decentralized data","volume-title":"Proc. 20th Int. Conf. Artif. Intell. Statist.","author":"McMahan","year":"2017"},{"key":"ref23","first-page":"429","article-title":"Federated optimization in heterogeneous networks","volume-title":"Proc. Mach. Learn. Syst.","author":"Li","year":"2020"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2021.3115952"},{"key":"ref25","article-title":"Communication-efficient admm-based federated learning","author":"Zhou","year":"2021"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3243080"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2023.3268845"},{"key":"ref28","first-page":"1","article-title":"Global convergence of multi-agent policy gradient in Markov potential games","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Leonardos","year":"2022"},{"key":"ref29","first-page":"1","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Kingma","year":"2015"},{"issue":"1","key":"ref30","first-page":"4431","article-title":"On the theory of policy gradient methods: Optimality, approximation, and distribution shift","volume":"22","author":"Agarwal","year":"2021","journal-title":"J. Mach. Learn. Res."},{"key":"ref31","article-title":"Study on LTE-based V2X services; (Release 14)","year":"2016"}],"container-title":["IEEE Journal of Selected Topics in Signal Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/4200690\/10849996\/10804630.pdf?arnumber=10804630","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,6]],"date-time":"2025-02-06T18:41:52Z","timestamp":1738867312000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10804630\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10]]},"references-count":31,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/jstsp.2024.3513692","relation":{},"ISSN":["1932-4553","1941-0484"],"issn-type":[{"value":"1932-4553","type":"print"},{"value":"1941-0484","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10]]}}}