{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T15:39:09Z","timestamp":1781019549981,"version":"3.54.1"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,12,4]],"date-time":"2022-12-04T00:00:00Z","timestamp":1670112000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,12,4]],"date-time":"2022-12-04T00:00:00Z","timestamp":1670112000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100003382","name":"CREST","doi-asserted-by":"publisher","award":["JPMJCR21D2"],"award-info":[{"award-number":["JPMJCR21D2"]}],"id":[{"id":"10.13039\/501100003382","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,12,4]]},"DOI":"10.1109\/globecom48099.2022.10000678","type":"proceedings-article","created":{"date-parts":[[2023,1,11]],"date-time":"2023-01-11T22:24:18Z","timestamp":1673475858000},"page":"1109-1114","source":"Crossref","is-referenced-by-count":3,"title":["Model-based Federated Reinforcement Distillation"],"prefix":"10.1109","author":[{"given":"Sefutsu","family":"Ryu","sequence":"first","affiliation":[{"name":"Graduate School of Information Science and Technology The University of Tokyo,Tokyo,Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shinya","family":"Takamaeda-Yamazaki","sequence":"additional","affiliation":[{"name":"Graduate School of Information Science and Technology The University of Tokyo,Tokyo,Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/tnn.1998.712192"},{"key":"ref2","first-page":"535","article-title":"An algorithm for distributed reinforcement learning in cooperative multi-agent systems","volume-title":"In Proceedings of the Seventeenth International Conference on Machine Learning","author":"Lauer","year":"2000"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2020.2975749"},{"key":"ref4","first-page":"20","article-title":"Communication-Efficient Learning of Deep Networks from Decentralized Data","volume-title":"Proceedings of the 20th International Conference on Artificial Intelligence and Statistics, ser. Proceedings of Machine Learning Research","volume":"54","author":"McMahan","year":"2017"},{"key":"ref5","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014","journal-title":"arXiv preprint"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1017\/9781108966559.019"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1201\/9781351006620-6"},{"issue":"3\u20134","key":"ref8","doi-asserted-by":"crossref","first-page":"279","DOI":"10.1007\/BF00992698","article-title":"Q-learning","volume":"8","author":"Watkins","year":"1992","journal-title":"Machine learning"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1561\/2200000086"},{"key":"ref10","author":"Hinton","year":"2015","journal-title":"Distilling the knowledge in a neural network"},{"key":"ref11","article-title":"Do deep nets really need to be deep?","author":"Ba","year":"2013","journal-title":"arXiv preprint"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/tmc.2021.3070013"},{"key":"ref13","article-title":"Group knowledge transfer: Federated learning of large cnns at the edge","author":"He","year":"2020","journal-title":"arXiv preprint"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/MIS.2020.2994942"},{"key":"ref15","author":"Wang","year":"2021","journal-title":"Federated ensemble model-based reinforcement learning"},{"issue":"22","key":"ref16","first-page":"1273","article-title":"Communication-Efficient Learning of Deep Networks from Decentralized Data","volume-title":"Proceedings of the 20th International Conference on Artificial Intelligence and Statistics","volume":"54","author":"McMahan","year":"2017"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2019.8761315"},{"key":"ref18","author":"Kone\u010dn\u00fd","year":"2017","journal-title":"Federated learning: Strategies for improving communication efficiency"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3912"},{"key":"ref20","article-title":"Playing atari with deep reinforcement learning","author":"Mnih","year":"2013","journal-title":"arXiv preprint"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref22","volume-title":"Reinforcement learning for robots using neural networks","author":"Lin","year":"1992"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"issue":"8","key":"ref24","first-page":"2","article-title":"Neural networks for machine learning lecture 6a overview of mini-batch gradient descent","volume":"14","author":"Hinton","year":"2012","journal-title":"Cited on"}],"event":{"name":"GLOBECOM 2022 - 2022 IEEE Global Communications Conference","location":"Rio de Janeiro, Brazil","start":{"date-parts":[[2022,12,4]]},"end":{"date-parts":[[2022,12,8]]}},"container-title":["GLOBECOM 2022 - 2022 IEEE Global Communications Conference"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10000063\/10000593\/10000678.pdf?arnumber=10000678","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,9]],"date-time":"2024-02-09T03:02:22Z","timestamp":1707447742000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10000678\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12,4]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/globecom48099.2022.10000678","relation":{},"subject":[],"published":{"date-parts":[[2022,12,4]]}}}