{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T21:02:51Z","timestamp":1768338171466,"version":"3.49.0"},"reference-count":19,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,12,16]],"date-time":"2024-12-16T00:00:00Z","timestamp":1734307200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,16]],"date-time":"2024-12-16T00:00:00Z","timestamp":1734307200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,12,16]]},"DOI":"10.1109\/cdc56724.2024.10886168","type":"proceedings-article","created":{"date-parts":[[2025,2,26]],"date-time":"2025-02-26T18:43:32Z","timestamp":1740595412000},"page":"2658-2663","source":"Crossref","is-referenced-by-count":1,"title":["Towards Fast Rates for Federated and Multi-Task Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Feng","family":"Zhu","sequence":"first","affiliation":[{"name":"North Carolina State University,Dept. of Electrical and Computer Engineering"}]},{"given":"Robert W.","family":"Heath","sequence":"additional","affiliation":[{"name":"University of California,Dept. of Electrical and Computer Engineering,San Diego,USA"}]},{"given":"Aritra","family":"Mitra","sequence":"additional","affiliation":[{"name":"North Carolina State University,Dept. of Electrical and Computer Engineering"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.20517\/ir.2021.02"},{"key":"ref2","first-page":"10997","article-title":"Federated reinforcement learning: Linear speedup under Markovian sampling","volume-title":"Int. Conf. on Machine Learning.","author":"Khodadadian"},{"key":"ref3","article-title":"Federated temporal difference learning with linear function approximation under environmental heterogeneity","author":"Wang","year":"2023","journal-title":"arXiv:2302.02212"},{"key":"ref4","first-page":"18","article-title":"Federated reinforcement learning with environment heterogeneity","volume-title":"International Conf. on Artificial Intelligence and Stat.","author":"Jin"},{"key":"ref5","first-page":"9767","article-title":"Multi-task reinforcement learning with context-based representations","volume-title":"International Conference on Machine Learning.","author":"Sodhani"},{"key":"ref6","first-page":"1273","article-title":"Communication-efficient learning of deep networks from decentralized data","author":"McMahan","year":"2017","journal-title":"AISTATS."},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2023.3242734"},{"key":"ref8","article-title":"A decentralized policy gradient approach to multi-task reinforcement learning","author":"Zeng","year":"2021","journal-title":"Uncertainty in Artificial Intelligence. PMLR"},{"key":"ref9","first-page":"6820","article-title":"On the global convergence rates of softmax policy gradient methods","volume-title":"Int. Conf. on Machine Learning.","author":"Mei"},{"key":"ref10","first-page":"3332","article-title":"A general sample complexity analysis of vanilla policy gradient","volume-title":"Int. Conf. on Artificial Intelligence and Statistics.","author":"Yuan"},{"key":"ref11","doi-asserted-by":"crossref","first-page":"331","DOI":"10.1016\/S0927-0507(05)80172-0","article-title":"Markov decision processes","volume":"2","author":"Puterman","year":"1990","journal-title":"Handbooks in Operations Research and Management Science"},{"issue":"98","key":"ref12","first-page":"1","article-title":"On the theory of policy gradient methods: Optimality, approximation, and distribution shift","volume":"22","author":"Agarwal","year":"2021","journal-title":"Journal of Machine Learning Research"},{"key":"ref13","article-title":"Policy gradient methods for reinforcement learning with function approximation","volume":"12","author":"Sutton","year":"1999","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref14","first-page":"14606","article-title":"Linear convergence in federated learning: Tackling client heterogeneity and sparse gradients","volume":"34","author":"Mitra","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref15","first-page":"5132","article-title":"Scaffold: Stochastic controlled averaging for federated learning","volume-title":"International Conference on Machine Learning.","author":"Karimireddy"},{"key":"ref16","first-page":"1467","article-title":"Global convergence of policy gradient methods for the linear quadratic regulator","volume-title":"Int. Conf. on Machine Learning.","author":"Fazel"},{"key":"ref17","volume-title":"Reinforcement learning: Theory and algorithms","volume":"32","author":"Agarwal","year":"2019"},{"issue":"282","key":"ref18","first-page":"1","article-title":"On the convergence rates of policy gradient methods","volume":"23","author":"Xiao","year":"2022","journal-title":"Journal of Machine Learning Research"},{"key":"ref19","article-title":"Towards fast rates for federated and multi-task reinforcement learning","author":"Zhu","year":"2024","journal-title":"arXiv preprint"}],"event":{"name":"2024 IEEE 63rd Conference on Decision and Control (CDC)","location":"Milan, Italy","start":{"date-parts":[[2024,12,16]]},"end":{"date-parts":[[2024,12,19]]}},"container-title":["2024 IEEE 63rd Conference on Decision and Control (CDC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10885784\/10885785\/10886168.pdf?arnumber=10886168","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,27]],"date-time":"2025-02-27T07:33:08Z","timestamp":1740641588000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10886168\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,16]]},"references-count":19,"URL":"https:\/\/doi.org\/10.1109\/cdc56724.2024.10886168","relation":{},"subject":[],"published":{"date-parts":[[2024,12,16]]}}}