{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T03:22:08Z","timestamp":1775186528657,"version":"3.50.1"},"reference-count":47,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2023,4,1]],"date-time":"2023-04-01T00:00:00Z","timestamp":1680307200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,4,1]],"date-time":"2023-04-01T00:00:00Z","timestamp":1680307200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,4,1]],"date-time":"2023-04-01T00:00:00Z","timestamp":1680307200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"NSFC\/RGC Joint Research Scheme","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002920","name":"Research Grants Council of the Hong Kong Special Administrative Region, China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002920","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["N_HKUST656\/22"],"award-info":[{"award-number":["N_HKUST656\/22"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE J. Select. Areas Commun."],"published-print":{"date-parts":[[2023,4]]},"DOI":"10.1109\/jsac.2023.3242734","type":"journal-article","created":{"date-parts":[[2023,2,6]],"date-time":"2023-02-06T18:45:39Z","timestamp":1675709139000},"page":"1227-1242","source":"Crossref","is-referenced-by-count":48,"title":["FedKL: Tackling Data Heterogeneity in Federated Reinforcement Learning by Penalizing KL Divergence"],"prefix":"10.1109","volume":"41","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2003-0472","authenticated-orcid":false,"given":"Zhijie","family":"Xie","sequence":"first","affiliation":[{"name":"Department of Electronic and Computer Engineering, The Hong Kong University of Science and Technology, Sai kung, Hong Kong"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6316-8415","authenticated-orcid":false,"given":"Shenghui","family":"Song","sequence":"additional","affiliation":[{"name":"Department of Electronic and Computer Engineering, The Hong Kong University of Science and Technology, Sai kung, Hong Kong"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Communication-efficient distributed reinforcement learning","author":"Chen","year":"2018","journal-title":"arXiv:1812.03239"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3298981"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2020.2975749"},{"key":"ref4","article-title":"Federated learning: Strategies for improving communication efficiency","author":"Kone\u010dn\u00fd","year":"2016","journal-title":"arXiv:1610.05492"},{"key":"ref5","first-page":"1","article-title":"QSGD: Communication-efficient SGD via gradient quantization and encoding","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Alistarh"},{"key":"ref6","first-page":"11082","article-title":"Local SGD with periodic averaging: Tighter analysis and adaptive synchronization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Haddadpour"},{"issue":"213","key":"ref7","first-page":"1","article-title":"Cooperative SGD: A unified framework for the design and analysis of local-update SGD algorithms","volume":"22","author":"Wang","year":"2021","journal-title":"J. Mach. Learn. Res."},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33015693"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.07.098"},{"key":"ref10","first-page":"1","article-title":"On the convergence of FedAvg on non-IID data","volume-title":"Proc. 8th Int. Conf. Learn. Represent.","author":"Li"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/tnn.1998.712192"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.20517\/ir.2021.02"},{"key":"ref13","first-page":"387","article-title":"Deterministic policy gradient algorithms","volume-title":"Proc. 31st Int. Conf. Int. Conf. Mach. Learn.","volume":"32","author":"Silver"},{"issue":"52","key":"ref14","first-page":"1","article-title":"Expected policy gradients for reinforcement learning","volume":"21","author":"Ciosek","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref15","first-page":"1","article-title":"Policy gradient methods for reinforcement learning with function approximation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"12","author":"Sutton"},{"key":"ref16","article-title":"Federated learning on non-IID data silos: An experimental study","author":"Li","year":"2021","journal-title":"arXiv:2102.02079"},{"key":"ref17","article-title":"Federated learning with non-IID data","author":"Zhao","year":"2018","journal-title":"arXiv:1806.00582"},{"key":"ref18","first-page":"1273","article-title":"Communication-efficient learning of deep networks from decentralized data","volume-title":"Proc. 20th Int. Conf. Artif. Intell. Statist.","volume":"54","author":"McMahan"},{"key":"ref19","first-page":"429","article-title":"Federated optimization in heterogeneous networks","volume-title":"Proc. Mach. Learn. Syst.","volume":"2","author":"Li"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM41043.2020.9155494"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8967908"},{"key":"ref22","article-title":"Federated reinforcement learning","author":"Zhuo","year":"2019","journal-title":"arXiv:2108.11887"},{"key":"ref23","article-title":"Federated transfer reinforcement learning for autonomous driving","author":"Liang","year":"2019","journal-title":"arXiv:1910.06001"},{"key":"ref24","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"},{"key":"ref25","first-page":"1008","article-title":"Actor-critic algorithms","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"12","author":"Konda"},{"key":"ref26","first-page":"6382","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume-title":"Proc. 31st Int. Conf. Neural Inf. Process. Syst.","author":"Lowe"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.3390\/s20051359"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3083087"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.2024.2310287"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICC42927.2021.9500603"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/twc.2023.3279268"},{"key":"ref32","first-page":"18","article-title":"Federated reinforcement learning with environment heterogeneity","volume-title":"Proc. 25th Int. Conf. Artif. Intell. Statist.","volume":"151","author":"Jin"},{"key":"ref33","first-page":"1","article-title":"High-dimensional continuous control using generalized advantage estimation","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Schulman"},{"key":"ref34","first-page":"1","article-title":"Fault-tolerant federated reinforcement learning with theoretical guarantee","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Fan"},{"key":"ref35","article-title":"Trust region policy optimization","author":"Schulman","year":"2015","journal-title":"arXiv:1502.05477"},{"key":"ref36","first-page":"267","article-title":"Approximately optimal approximate reinforcement learning","volume-title":"Proc. 19th Int. Conf. Mach. Learn.","author":"Kakade"},{"key":"ref37","first-page":"22","article-title":"Constrained policy optimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Achiam"},{"key":"ref38","article-title":"Trust region policy optimisation in multi-agent reinforcement learning","author":"Kuba","year":"2022","journal-title":"arXiv:2109.11251"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511921889"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref41","article-title":"Openai gym","author":"Brockman","year":"2016","journal-title":"arXiv:1606.01540"},{"key":"ref42","first-page":"399","article-title":"Benchmarks for reinforcement learning in mixed-autonomy traffic","volume-title":"Proc. 2nd Conf. Robot Learn.","volume":"87","author":"Vinitsky"},{"key":"ref43","first-page":"1","article-title":"A natural policy gradient","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"14","author":"Kakade"},{"key":"ref44","first-page":"1","article-title":"Covariant policy search","volume-title":"Proc. IJCAI","author":"Bagnell"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICC40277.2020.9148862"},{"key":"ref46","article-title":"An inequality for the trace of matrix products, using absolute values","author":"Baumgartner","year":"2011","journal-title":"arXiv:1106.6189"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1198\/0003130042836"}],"container-title":["IEEE Journal on Selected Areas in Communications"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/49\/10075675\/10038492.pdf?arnumber=10038492","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,14]],"date-time":"2024-03-14T05:56:23Z","timestamp":1710395783000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10038492\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,4]]},"references-count":47,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/jsac.2023.3242734","relation":{},"ISSN":["0733-8716","1558-0008"],"issn-type":[{"value":"0733-8716","type":"print"},{"value":"1558-0008","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,4]]}}}