{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,5]],"date-time":"2026-03-05T22:41:44Z","timestamp":1772750504905,"version":"3.50.1"},"reference-count":63,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62341201"],"award-info":[{"award-number":["62341201"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62072472"],"award-info":[{"award-number":["62072472"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62172445"],"award-info":[{"award-number":["62172445"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62302260"],"award-info":[{"award-number":["62302260"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62432004"],"award-info":[{"award-number":["62432004"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62402267"],"award-info":[{"award-number":["62402267"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62472355"],"award-info":[{"award-number":["62472355"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"crossref","award":["2023M731956"],"award-info":[{"award-number":["2023M731956"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Postdoctoral Fellowship Program of CPSF","award":["GZB20230352"],"award-info":[{"award-number":["GZB20230352"]}]},{"DOI":"10.13039\/501100001809","name":"Guoqiang Institute, Tsinghua University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Netw."],"published-print":{"date-parts":[[2025,4]]},"DOI":"10.1109\/tnet.2024.3510352","type":"journal-article","created":{"date-parts":[[2024,12,18]],"date-time":"2024-12-18T19:57:14Z","timestamp":1734551834000},"page":"865-880","source":"Crossref","is-referenced-by-count":2,"title":["Momentum-Based Contextual Federated Reinforcement Learning"],"prefix":"10.1109","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-3416-8181","authenticated-orcid":false,"given":"Sheng","family":"Yue","sequence":"first","affiliation":[{"name":"Department of Computer Science and Technology, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xingyuan","family":"Hua","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yongheng","family":"Deng","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lili","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Electronics and Information, Northwestern Polytechnical University, Xi’an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2782-183X","authenticated-orcid":false,"given":"Ju","family":"Ren","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6717-461X","authenticated-orcid":false,"given":"Yaoxue","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM52122.2024.10621260"},{"key":"ref2","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":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2021.3119950"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2023.3316189"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2931179"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/AIKE.2019.00031"},{"key":"ref7","article-title":"Federated deep reinforcement learning","volume-title":"arXiv:1901.08277","author":"Zhuo","year":"2019"},{"key":"ref8","first-page":"1007","article-title":"Fault-tolerant federated reinforcement learning with theoretical guarantee","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Fan"},{"key":"ref9","first-page":"10997","article-title":"Federated reinforcement learning: Linear speedup under Markovian sampling","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Khodadadian"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-11748-0_15"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.3026589"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.3390\/s20051359"},{"key":"ref13","first-page":"2211","article-title":"Achieving linear speedup with partial worker participation in non-IID federated learning","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","volume":"3","author":"Yang"},{"key":"ref14","article-title":"Multi-task federated reinforcement learning with adversaries","volume-title":"arXiv:2103.06473","author":"Anwar","year":"2021"},{"key":"ref15","first-page":"315","article-title":"Accelerating stochastic gradient descent using predictive variance reduction","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"26","author":"Johnson"},{"key":"ref16","first-page":"5132","article-title":"SCAFFOLD: Stochastic controlled averaging for federated learning","volume-title":"Proc. 37th Int. Conf. Mach. Learn.","volume":"119","author":"Karimireddy"},{"key":"ref17","first-page":"6050","article-title":"STEM: A stochastic two-sided momentum algorithm achieving near-optimal sample and communication complexities for federated learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Khanduri"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01712"},{"key":"ref19","first-page":"1094","article-title":"Meta-world: A benchmark and evaluation for multi-task and meta reinforcement learning","volume-title":"Proc. Conf. Robot Learn. (CoRL)","author":"Yu"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2022.3204796"},{"key":"ref21","first-page":"3557","article-title":"Personalized federated learning with theoretical guarantees: A model-agnostic meta-learning approach","volume-title":"Proc. NeurIPS Conf.","volume":"33","author":"Fallah"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3466772.3467038"},{"key":"ref23","first-page":"429","article-title":"Federated optimization in heterogeneous networks","volume-title":"Proc. 3rd Mach. Learn. Syst. Conf.","author":"Li"},{"key":"ref24","first-page":"9767","article-title":"Multi-task reinforcement learning with context-based representations","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Sodhani"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1049\/cje.2016.11.016"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2019.2918951"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.23919\/cje.2022.00.031"},{"key":"ref28","first-page":"2613","article-title":"Double Q-learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"23","author":"Hasselt"},{"key":"ref29","article-title":"Proximal policy optimization algorithms","volume-title":"arXiv:1707.06347","author":"Schulman","year":"2017"},{"key":"ref30","article-title":"Continuous control with deep reinforcement learning","volume-title":"arXiv:1509.02971","author":"Lillicrap","year":"2015"},{"key":"ref31","article-title":"Federated reinforcement distillation with proxy experience memory","volume-title":"arXiv:1907.06536","author":"Cha","year":"2019"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref33","first-page":"2419","article-title":"Challenges of real-world reinforcement learning","volume-title":"Proc. ICML Workshop Real-Life Reinforcement Learn.","author":"Mankowitz"},{"key":"ref34","first-page":"18","article-title":"Federated reinforcement learning with environment heterogeneity","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Jin"},{"key":"ref35","first-page":"4424","article-title":"Federated multi-task learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Smith"},{"key":"ref36","article-title":"Federated learning with personalization layers","volume-title":"arXiv:1912.00818","author":"Arivazhagan","year":"2019"},{"key":"ref37","first-page":"15434","article-title":"Federated multi-task learning under a mixture of distributions","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Marfoq"},{"key":"ref38","article-title":"Federated meta-learning with fast convergence and efficient communication","volume-title":"arXiv:1802.07876","author":"Chen","year":"2018"},{"key":"ref39","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","volume":"70","author":"Finn"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1023\/A:1007379606734"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10599-4_7"},{"key":"ref42","first-page":"4496","article-title":"Distral: Robust multitask reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Teh"},{"key":"ref43","first-page":"1719","article-title":"EPOpt: Learning robust neural network policies using model ensembles","volume-title":"Proc. Int. Conf. Represent. Learn. (ICLR)","author":"Rajeswaran"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.579"},{"issue":"8","key":"ref45","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI Blog"},{"key":"ref46","first-page":"12350","article-title":"Towards interpretable reinforcement learning using attention augmented agents","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Mott"},{"key":"ref47","first-page":"5824","article-title":"Gradient surgery for multi-task learning","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Yu"},{"key":"ref48","first-page":"18878","article-title":"Conflict-averse gradient descent for multi-task learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","author":"Liu"},{"key":"ref49","first-page":"21495","article-title":"PaCo: Parameter-compositional multi-task reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Sun"},{"key":"ref50","first-page":"4767","article-title":"Multi-task reinforcement learning with soft modularization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Yang"},{"key":"ref51","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton","year":"2018"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4615-3618-5_2"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1613\/jair.806"},{"key":"ref54","article-title":"Reinforcement learning: Theory and algorithms","volume-title":"Tech. Rep.","author":"Agarwal","year":"2019"},{"key":"ref55","first-page":"7184","article-title":"On the linear speedup analysis of communication efficient momentum SGD for distributed non-convex optimization","volume-title":"Proc. 36th Int. Conf. Machine Learning, (ICML)","author":"Yu"},{"key":"ref56","article-title":"Mime: Mimicking centralized stochastic algorithms in federated learning","volume-title":"arXiv:2008.03606","author":"Karimireddy","year":"2020"},{"key":"ref57","first-page":"4026","article-title":"Stochastic variance-reduced policy gradient","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Papini"},{"key":"ref58","first-page":"541","article-title":"An improved convergence analysis of stochastic variance-reduced policy gradient","volume-title":"Proc. Uncertainty Artif. Intell. Conf.","author":"Xu"},{"key":"ref59","first-page":"2658","article-title":"The complexity of finding stationary points with stochastic gradient descent","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Drori"},{"key":"ref60","first-page":"442","article-title":"Learning bounds for importance weighting","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"23","author":"Cortes"},{"key":"ref61","article-title":"OpenAI Gym","volume-title":"arXiv:1606.01540","author":"Brockman","year":"2016"},{"key":"ref62","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Haarnoja"},{"key":"ref63","first-page":"36507","article-title":"Contrastive modules with temporal attention for multi-task reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Lan"}],"container-title":["IEEE Transactions on Networking"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10723154\/10969151\/10806823.pdf?arnumber=10806823","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,18]],"date-time":"2025-04-18T17:36:14Z","timestamp":1744997774000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10806823\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4]]},"references-count":63,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tnet.2024.3510352","relation":{},"ISSN":["2998-4157"],"issn-type":[{"value":"2998-4157","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4]]}}}