{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T15:05:25Z","timestamp":1777388725268,"version":"3.51.4"},"reference-count":33,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,7,12]],"date-time":"2022-07-12T00:00:00Z","timestamp":1657584000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,7,12]],"date-time":"2022-07-12T00:00:00Z","timestamp":1657584000000},"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":[[2022,7,12]]},"DOI":"10.23919\/ecc55457.2022.9837987","type":"proceedings-article","created":{"date-parts":[[2022,8,5]],"date-time":"2022-08-05T19:33:46Z","timestamp":1659728026000},"page":"1890-1895","source":"Crossref","is-referenced-by-count":2,"title":["Federated Reinforcement Learning at the Edge: Exploring the Learning-Communication Tradeoff"],"prefix":"10.23919","author":[{"given":"Konstantinos","family":"Gatsis","sequence":"first","affiliation":[{"name":"University of Oxford,Department of Engineering Science,Oxford,UK.,OX1 3PJ"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","author":"gatsis","year":"2021","journal-title":"Federated reinforcement learning at the edge"},{"key":"ref32","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":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/11564096_32"},{"key":"ref30","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref10","first-page":"2021","article-title":"Fedpaq: A communication-efficient federated learning method with periodic averaging and quantization","author":"reisizadeh","year":"0","journal-title":"International Conference on Artificial Intelligence and Statistics"},{"key":"ref11","article-title":"Scheduling policies for federated learning in wireless networks","author":"yang","year":"2019","journal-title":"IEEE Transactions on Communications"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.23919\/ACC50511.2021.9482692"},{"key":"ref13","article-title":"Linear regression over networks with communication guar-antees","author":"gatsis","year":"0","journal-title":"3rd Annual Learning for Dynamics & Control Conference"},{"key":"ref14","first-page":"3943","article-title":"Lena: Communication-efficient distributed learning with self-triggered gradient uploads","author":"ghadikolaei","year":"2021","journal-title":"International Conference on Artificial Intelligence and Statistics"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CDC42340.2020.9303828"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TCNS.2021.3078100"},{"key":"ref17","author":"ornia","year":"2021","journal-title":"Event-based communication in multi-agent distributed q-learning"},{"key":"ref18","author":"mitra","year":"2021","journal-title":"Robust federated best-arm iden-tification in multi-armed bandits"},{"key":"ref19","first-page":"247","article-title":"Communication efficient parallel reinforcement learning","author":"agarwal","year":"2021","journal-title":"Uncertainty in Artificial Intelli-gence"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1177\/0278364917710318"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CDC40024.2019.9029969"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.sigpro.2015.01.019"},{"key":"ref3","first-page":"5872","article-title":"Fully decen-tralized multi-agent reinforcement learning with networked agents","author":"zhang","year":"2018","journal-title":"International Conference on Machine Learning"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1137\/20M1311971"},{"key":"ref29","author":"bertsekas","year":"2012","journal-title":"Dynamic Programming and Optimal Control Athena Scientific Belmont MA"},{"key":"ref5","article-title":"Multi-agent fully decen-tralized value function learning with linear convergence rates","author":"cassano","year":"0","journal-title":"IEEE Transactions on Automatic Control 2020"},{"key":"ref8","author":"konecny","year":"2016","journal-title":"Federated learning Strategies for improving communication efficiency"},{"key":"ref7","first-page":"671","article-title":"Learning decentralized controllers for robot swarms with graph neural networks","author":"tolstaya","year":"2020","journal-title":"Conference on Robot Learning"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1137\/19M1291108"},{"key":"ref9","first-page":"5050","article-title":"Lag: Lazily aggregated gradient for communication-efficient distributed learning","author":"chen","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref1","first-page":"256","article-title":"Scalable reinforcement learning of localized policies for multi-agent networked systems","author":"qu","year":"2020","journal-title":"Learning for Dynamics and Control"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2019.2909198"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.23919\/ACC.2018.8431102"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/LCSYS.2020.3006008"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2020.3031073"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/MLHPCAI4S51975.2020.00008"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1561\/2200000051"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2017.2743678"}],"event":{"name":"2022 European Control Conference (ECC)","location":"London, United Kingdom","start":{"date-parts":[[2022,7,12]]},"end":{"date-parts":[[2022,7,15]]}},"container-title":["2022 European Control Conference (ECC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9837955\/9837961\/09837987.pdf?arnumber=9837987","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,4,24]],"date-time":"2023-04-24T18:17:28Z","timestamp":1682360248000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9837987\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7,12]]},"references-count":33,"URL":"https:\/\/doi.org\/10.23919\/ecc55457.2022.9837987","relation":{},"subject":[],"published":{"date-parts":[[2022,7,12]]}}}