{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T16:15:40Z","timestamp":1774455340899,"version":"3.50.1"},"reference-count":33,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100003725","name":"Basic Science Research Program through the National Research Foundation of Korea (NRF) by the Ministry of Education","doi-asserted-by":"publisher","award":["2018R1A6A1A03025526"],"award-info":[{"award-number":["2018R1A6A1A03025526"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003725","name":"Basic Science Research Program through the National Research Foundation of Korea (NRF) by the Ministry of Education","doi-asserted-by":"publisher","award":["NRF- 2020R1A6A3A13073735"],"award-info":[{"award-number":["NRF- 2020R1A6A3A13073735"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/access.2021.3083087","type":"journal-article","created":{"date-parts":[[2021,5,24]],"date-time":"2021-05-24T19:47:47Z","timestamp":1621885667000},"page":"76296-76306","source":"Crossref","is-referenced-by-count":22,"title":["Federated Reinforcement Learning Acceleration Method for Precise Control of Multiple Devices"],"prefix":"10.1109","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8807-1158","authenticated-orcid":false,"given":"Hyun-Kyo","family":"Lim","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6406-3092","authenticated-orcid":false,"given":"Ju-Bong","family":"Kim","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5204-2283","authenticated-orcid":false,"given":"Ihsan","family":"Ullah","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Joo-Seong","family":"Heo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5835-7972","authenticated-orcid":false,"given":"Youn-Hee","family":"Han","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","first-page":"825","article-title":"Information theory and statistics. Solomon Kullback","volume":"54","author":"lindley","year":"1959","journal-title":"J Amer Stat Assoc"},{"key":"ref32","article-title":"High-dimensional continuous control using generalized advantage estimation","author":"schulman","year":"2015","journal-title":"arXiv 1506 02438 [cs]"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.3390\/app10165722"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.11396"},{"key":"ref10","article-title":"Federated optimization: Distributed optimization beyond the datacenter","author":"konecn\u00fd","year":"2015","journal-title":"arXiv1511 03575"},{"key":"ref11","article-title":"Federated transfer reinforcement learning for autonomous driving","author":"liang","year":"2019","journal-title":"arXiv 1910 06001"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2931179"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.2986803"},{"key":"ref14","article-title":"Federated control with hierarchical multi-agent deep reinforcement learning","author":"kumar","year":"2017","journal-title":"arXiv 1712 08266"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2905621"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.3390\/s20051359"},{"key":"ref17","first-page":"1868","article-title":"Federated reinforcement learning for automatic control in sdn-based iot environments","author":"lim","year":"2020","journal-title":"Proc Int Conf Inf Commun Technol Converg (ICTC)"},{"key":"ref18","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"arXiv 1707 06347"},{"key":"ref19","article-title":"Actor-critic algorithms","author":"konda","year":"2002"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/BRACIS.2016.027"},{"key":"ref4","article-title":"Benchmarking deep reinforcement learning for continuous control","author":"duan","year":"2016","journal-title":"Proc ICML"},{"key":"ref27","first-page":"3982","article-title":"Transfer learning for multiagent reinforcement learning systems","author":"da silva","year":"2016","journal-title":"Proc 25th Int Joint Conf Artif Intell"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0172395"},{"key":"ref29","first-page":"263","article-title":"Transfer learning for multi-agent coordination","author":"vrancx","year":"2011","journal-title":"Proc 3th Int Conf Agents Artif Intell"},{"key":"ref5","article-title":"Reinforcement learning and deep learning based lateral control for autonomous driving","author":"li","year":"2018","journal-title":"arXiv 1810 12778"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/DASC.2018.8569503"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.3021017"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2020.2988367"},{"key":"ref1","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref20","first-page":"6382","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","author":"lowe","year":"2017","journal-title":"Proc 31st Int Conf Neural Inf Process Syst"},{"key":"ref22","article-title":"Multi-agent reinforcement learning: A selective overview of theories and algorithms","author":"zhang","year":"2019","journal-title":"arXiv 1911 10635"},{"key":"ref21","first-page":"1889","article-title":"Trust region policy optimization","volume":"37","author":"schulman","year":"2015","journal-title":"Proc 32nd Int Conf Mach Learn"},{"key":"ref24","article-title":"Towards federated learning at scale: System design","author":"bonawitz","year":"2019","journal-title":"arXiv 1902 01046"},{"key":"ref23","first-page":"1273","article-title":"Communication-efficient learning of deep networks from decentralized data","volume":"54","author":"mcmahan","year":"2017","journal-title":"Proc AISTATS"},{"key":"ref26","first-page":"1633","article-title":"Transfer learning for reinforcement learning domains: A survey","volume":"10","author":"taylor","year":"2009","journal-title":"J Mach Learn Res"},{"key":"ref25","article-title":"Federated reinforcement learning","author":"zhuo","year":"2019","journal-title":"arXiv 1901 08277"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9312710\/09439484.pdf?arnumber=9439484","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,12,17]],"date-time":"2021-12-17T19:56:16Z","timestamp":1639770976000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9439484\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/access.2021.3083087","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}