{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T05:19:46Z","timestamp":1782278386161,"version":"3.54.5"},"reference-count":49,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"EU Horizon 2020 INITIATE Project","award":["101008297"],"award-info":[{"award-number":["101008297"]}]},{"name":"Royal Society International Exchanges Project","award":["IEC\/NSFC\/ 211460"],"award-info":[{"award-number":["IEC\/NSFC\/ 211460"]}]},{"name":"EPSRC New Horizons","award":["EP\/X019160\/1"],"award-info":[{"award-number":["EP\/X019160\/1"]}]},{"name":"UKRI Project","award":["EP\/X038866\/1"],"award-info":[{"award-number":["EP\/X038866\/1"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Parallel Distrib. Syst."],"published-print":{"date-parts":[[2023,6]]},"DOI":"10.1109\/tpds.2023.3264480","type":"journal-article","created":{"date-parts":[[2023,4,5]],"date-time":"2023-04-05T17:55:39Z","timestamp":1680717339000},"page":"1848-1859","source":"Crossref","is-referenced-by-count":36,"title":["Federated Ensemble Model-Based Reinforcement Learning in Edge Computing"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2487-2148","authenticated-orcid":false,"given":"Jin","family":"Wang","sequence":"first","affiliation":[{"name":"Department of Computer Science, University of Exeter, Exeter, U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5406-8420","authenticated-orcid":false,"given":"Jia","family":"Hu","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Exeter, Exeter, U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6344-9364","authenticated-orcid":false,"given":"Jed","family":"Mills","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Exeter, Exeter, U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1395-7314","authenticated-orcid":false,"given":"Geyong","family":"Min","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Exeter, Exeter, U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-2472-7735","authenticated-orcid":false,"given":"Ming","family":"Xia","sequence":"additional","affiliation":[{"name":"Google, Mountain View, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9746-3236","authenticated-orcid":false,"given":"Nektarios","family":"Georgalas","sequence":"additional","affiliation":[{"name":"Applied Research Department, British Telecom, London, U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"ref2","article-title":"Adaptive federated\n                    optimization","volume-title":"Proc. Int. Conf. Learn.\n                        Representations","author":"Reddi"},{"key":"ref3","article-title":"On the convergence of fedavg on non-IID\n                        data","volume-title":"Proc. Int. Conf. Learn.\n                        Representations","author":"Li"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1561\/9781680837896"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2020.2975189"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2020.3009406"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/tc.2021.3074806"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.3026589"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2020.3036946"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2021.3123500"},{"key":"ref11","article-title":"When to trust your model: Model-based policy\n                        optimization","volume-title":"Proc. Adv. Neural Inf.\n                        Process. Syst.","author":"Janner"},{"key":"ref12","article-title":"Model-ensemble trust-region policy\n                        optimization","volume-title":"Proc. Int. Conf. Learn.\n                        Representations","author":"Kurutach"},{"key":"ref13","article-title":"Model based reinforcement learning for\n                        atari","volume-title":"Proc. Int. Conf. Learn.\n                        Representations","author":"Kaiser"},{"key":"ref14","first-page":"1329","article-title":"Benchmarking deep reinforcement learning for\n                        continuous control","volume-title":"Proc. Int. Conf.\n                        Mach. Learn.","author":"Duan"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/AIKE.2019.00031"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1142\/9789811292552_0013"},{"key":"ref17","article-title":"Deep reinforcement learning in a handful of trials\n                        using probabilistic dynamics models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chua"},{"key":"ref18","first-page":"1338","article-title":"Asynchronous methods for model-based reinforcement\n                        learning","volume-title":"Proc. Conf. Robot\n                        Learn.","author":"Zhang"},{"key":"ref19","article-title":"Algorithmic framework for model-based deep\n                        reinforcement learning with theoretical guarantees","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Luo"},{"key":"ref20","article-title":"Dual policy iteration","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Sun"},{"key":"ref21","first-page":"21810","article-title":"Morel: Model-based offline reinforcement\n                        learning","volume-title":"Proc. Adv. Neural Inf. Process.\n                        Syst.","author":"Kidambi"},{"key":"ref22","article-title":"FedBE: Making Bayesian model ensemble applicable to\n                        federated learning","volume-title":"Proc. Int. Conf.\n                        Learn. Representations","author":"Chen"},{"key":"ref23","article-title":"Ensemble distillation for robust model fusion in\n                        federated learning","volume-title":"Proc. Adv. Neural\n                        Inf. Process. Syst.","author":"Lin"},{"key":"ref24","first-page":"465","article-title":"PILCO: A model-based and data-efficient approach to\n                        policy search","volume-title":"Proc. Int. Conf. Mach.\n                        Learn.","author":"Deisenroth"},{"key":"ref25","article-title":"Learning neural network policies with guided policy\n                        search under unknown dynamics","volume-title":"Proc. Adv.\n                        Neural Inf. Process. Syst.","author":"Levine"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386025"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2011.2159412"},{"key":"ref28","article-title":"Learning and policy search in stochastic dynamical\n                        systems with Bayesian neural networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Depeweg"},{"issue":"5","key":"ref29","doi-asserted-by":"crossref","first-page":"61","DOI":"10.1109\/37.466261","article-title":"Model predictive control using neural\n                        networks","volume":"15","author":"Draeger","year":"1995","journal-title":"IEEE Control\n                        Syst. Mag."},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8463189"},{"key":"ref31","first-page":"1273","article-title":"Communication-efficient learning of deep networks\n                        from decentralized data","volume-title":"Proc. Int. Conf.\n                        Artifical Intell. Statist.","author":"McMahan"},{"key":"ref32","first-page":"4387","article-title":"The non-IID data quagmire of decentralized machine\n                        learning","volume-title":"Proc. Int. Conf. Mach.\n                        Learn.","author":"Hsieh"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/JCN.2020.000015"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.2986803"},{"key":"ref35","article-title":"Adam: A method for stochastic\n                        optimization","volume-title":"Proc. Int. Conf. Learn.\n                        Representations","author":"Kingma"},{"key":"ref36","first-page":"1889","article-title":"Trust region policy\n                    optimization","volume-title":"Proc. Int. Conf. Mach.\n                        Learn.","author":"Schulman"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9781107298019"},{"key":"ref38","article-title":"MOPO: Model-based offline policy\n                        optimization","volume-title":"Proc. Adv. Neural Inf.\n                        Process. Syst.","author":"Yu"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2021.3134709"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2018.1701231"},{"key":"ref41","article-title":"High-dimensional continuous control using generalized\n                        advantage estimation","author":"Schulman","year":"2015"},{"key":"ref42","article-title":"Proximal policy optimization\n                        algorithms","author":"Schulman","year":"2017"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2931179"},{"key":"ref44","first-page":"5132","article-title":"SCAFFOLD: Stochastic controlled averaging for\n                        federated learning","volume-title":"Proc. Int. Conf.\n                        Mach. Learn.","author":"Karimireddy"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2017.2682318"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-021-05961-4"},{"key":"ref47","first-page":"3907","article-title":"OOD-MAML: Meta-learning for few-shot\n                        out-of-distribution detection and classification","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Jeong"},{"key":"ref48","article-title":"Learning to adapt in dynamic, real-world\n                        environments through meta-reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Nagabandi"},{"key":"ref49","volume-title":"Foundations of Machine Learning","author":"Mohri","year":"2018"}],"container-title":["IEEE Transactions on Parallel and Distributed Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/71\/10123122\/10093139.pdf?arnumber=10093139","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,10]],"date-time":"2024-09-10T04:28:39Z","timestamp":1725942519000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10093139\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6]]},"references-count":49,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tpds.2023.3264480","relation":{},"ISSN":["1045-9219","1558-2183","2161-9883"],"issn-type":[{"value":"1045-9219","type":"print"},{"value":"1558-2183","type":"electronic"},{"value":"2161-9883","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,6]]}}}