{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T16:25:24Z","timestamp":1775665524667,"version":"3.50.1"},"reference-count":18,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,2,1]],"date-time":"2020-02-01T00:00:00Z","timestamp":1580515200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,2,1]],"date-time":"2020-02-01T00:00:00Z","timestamp":1580515200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,2,1]],"date-time":"2020-02-01T00:00:00Z","timestamp":1580515200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020,2]]},"DOI":"10.1109\/icaiic48513.2020.9065233","type":"proceedings-article","created":{"date-parts":[[2020,4,17]],"date-time":"2020-04-17T01:46:17Z","timestamp":1587087977000},"page":"463-464","source":"Crossref","is-referenced-by-count":18,"title":["Federated Reinforcement Learning for Controlling Multiple Rotary Inverted Pendulums in Edge Computing Environments"],"prefix":"10.1109","author":[{"given":"Hyun-Kyo","family":"Lim","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ju-Bong","family":"Kim","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chan-Myung","family":"Kim","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gyu-Young","family":"Hwang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ho-bin","family":"Choi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Youn-Hee","family":"Han","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","author":"konda","year":"2002","journal-title":"Actor-critic algorithms"},{"key":"ref11","first-page":"6382","article-title":"Multi-agent Actor-Critic for Mixed Cooperative-Competitive Environments","author":"lowe","year":"2017","journal-title":"Proceedings of the 31st International Conference on Neural Information Processing Systems"},{"key":"ref12","article-title":"Federated Reinforcement Learning","volume":"abs 1901 8277","author":"zhuo","year":"2019","journal-title":"CoRR"},{"key":"ref13","volume":"abs 1910 6001","author":"liang","year":"2019","journal-title":"Federated Transfer Reinforcement Learning for Autonomous Driving"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2931179"},{"key":"ref15","year":"0","journal-title":"Qube - servo 2"},{"key":"ref16","first-page":"1488","article-title":"Scalable Distributed DNN Training using Commodity GPU Cloud Computing","author":"strom","year":"2015","journal-title":"Proceedings of Interspeech"},{"key":"ref17","article-title":"High-Dimensional Continuous Control Using Generalized Advantage Estimation","author":"schulman","year":"2015","journal-title":"CoRR"},{"key":"ref18","article-title":"Adam: A Method for Stochastic Optimization","author":"kingma","year":"2015","journal-title":"Proceedings of International Conference on Learning Representations"},{"key":"ref4","first-page":"1","article-title":"Reinforcement Learning-based Control of Nonlinear Systems using Lyapunov Stability Concept and Fuzzy Reward Scheme","author":"chen","year":"2019","journal-title":"IEEE Transactions on Circuits and Systems II Express Briefs"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ChiCC.2015.7260128"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/DASC.2018.8569503"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICEEE.2018.8533946"},{"key":"ref8","volume":"abs 1902 1046","author":"bonawitz","year":"2019","journal-title":"Towards Federated Learning at Scale System Design"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2905621"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-Level Control through Deep Reinforcement Learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref1","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref9","article-title":"Proximal Policy Optimization Algorithms","volume":"abs 1707 6347","author":"schulman","year":"2017","journal-title":"CoRR"}],"event":{"name":"2020 International Conference on Artificial Intelligence in Information and Communication (ICAIIC)","location":"Fukuoka, Japan","start":{"date-parts":[[2020,2,19]]},"end":{"date-parts":[[2020,2,21]]}},"container-title":["2020 International Conference on Artificial Intelligence in Information and Communication (ICAIIC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9046688\/9064864\/09065233.pdf?arnumber=9065233","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,27]],"date-time":"2022-06-27T20:15:50Z","timestamp":1656360950000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9065233\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,2]]},"references-count":18,"URL":"https:\/\/doi.org\/10.1109\/icaiic48513.2020.9065233","relation":{},"subject":[],"published":{"date-parts":[[2020,2]]}}}