{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T04:59:40Z","timestamp":1768280380925,"version":"3.49.0"},"reference-count":43,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2024YFE0200300"],"award-info":[{"award-number":["2024YFE0200300"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62271513"],"award-info":[{"award-number":["62271513"]}],"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":["62301328"],"award-info":[{"award-number":["62301328"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100021171","name":"Basic and Applied Basic Research Foundation of Guangdong Province","doi-asserted-by":"publisher","award":["2024A1515012015"],"award-info":[{"award-number":["2024A1515012015"]}],"id":[{"id":"10.13039\/501100021171","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100021171","name":"Basic and Applied Basic Research Foundation of Guangdong Province","doi-asserted-by":"publisher","award":["2025A1515010235"],"award-info":[{"award-number":["2025A1515010235"]}],"id":[{"id":"10.13039\/501100021171","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shenzhen Science and Technology Program","award":["CJGJZD20240729142100001"],"award-info":[{"award-number":["CJGJZD20240729142100001"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Commun."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tcomm.2025.3631558","type":"journal-article","created":{"date-parts":[[2025,11,11]],"date-time":"2025-11-11T18:27:32Z","timestamp":1762885652000},"page":"870-885","source":"Crossref","is-referenced-by-count":2,"title":["Meta-Reinforcement Learning With Mixture of Experts for Generalizable Multi Access in Heterogeneous Wireless Networks"],"prefix":"10.1109","volume":"74","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-6066-1307","authenticated-orcid":false,"given":"Zhaoyang","family":"Liu","sequence":"first","affiliation":[{"name":"School of Electronics and Information Technology, Sun Yat-sen University, Guangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3504-9763","authenticated-orcid":false,"given":"Xijun","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Electronics and Information Technology, Sun Yat-sen University, Guangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1758-9213","authenticated-orcid":false,"given":"Chenyuan","family":"Feng","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Exeter, Exeter, U.K."}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0621-1469","authenticated-orcid":false,"given":"Xinghua","family":"Sun","sequence":"additional","affiliation":[{"name":"School of Electronics and Communication Engineering, Sun Yat-sen University, Shenzhen, China"}]},{"given":"Wen","family":"Zhan","sequence":"additional","affiliation":[{"name":"School of Electronics and Communication Engineering, Sun Yat-sen University, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9800-6472","authenticated-orcid":false,"given":"Xiang","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Electronics and Information Technology, Sun Yat-sen University, Guangzhou, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.23919\/WiOpt58741.2023.10349896"},{"key":"ref2","volume-title":"DARPA SC2 Website","year":"2018"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/MSPEC.2019.8727143"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2019.2904329"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2021.3099495"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2020.2990399"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICC45855.2022.9838618"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2020.3029844"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3170050"},{"key":"ref10","article-title":"Reinforcement learning for improved random access in delay-constrained heterogeneous wireless networks","author":"Deng","year":"2022","journal-title":"arXiv:2205.02057"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2021.3057826"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICC45855.2022.9838614"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2024.3432530"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2022.3143251"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/WCNC55385.2023.10119114"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2022.3210955"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCC55456.2022.9880665"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2019.8761566"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/WCNC51071.2022.9771953"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1561\/2200000080"},{"key":"ref22","article-title":"RL2: Fast reinforcement learning via slow reinforcement learning","author":"Duan","year":"2016","journal-title":"arXiv:1611.02779"},{"key":"ref23","first-page":"1","article-title":"Meta-Q-learning","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Fakoor"},{"key":"ref24","first-page":"5331","article-title":"Efficient off-policy meta-reinforcement learning via probabilistic context variables","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Rakelly"},{"key":"ref25","first-page":"1","article-title":"Auto-encoding variational Bayes","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Kingma"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3185549"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3417114"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2012.2200299"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095401"},{"key":"ref30","first-page":"1","article-title":"Multimodal contrastive learning with LIMoE: The language-image mixture of experts","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Mustafa"},{"key":"ref31","first-page":"1","article-title":"Theory on mixture-of-experts in continual learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Li"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM55648.2025.11044567"},{"key":"ref33","first-page":"1","article-title":"Multi-task reinforcement learning with mixture of orthogonal experts","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Hendawy"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i19.34209"},{"key":"ref35","first-page":"1","article-title":"Data-free one-shot federated learning under very high statistical heterogeneity","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Heinbaugh"},{"key":"ref36","article-title":"On meta-reinforcement learning in task distributions with varying dynamics","author":"Retyk","year":"2021"},{"key":"ref37","first-page":"1856","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":"ref38","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1812.05905"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/320941.320947"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref41","first-page":"2613","article-title":"Double Q-learning","volume-title":"Proc. Neural Inf. Process. Syst. (NIPS)","author":"Hasselt"},{"key":"ref42","article-title":"A quantitative measure of fairness and discrimination for resource allocation in shared computer systems","author":"Jain","year":"1984"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2024.3382289"}],"container-title":["IEEE Transactions on Communications"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/26\/11320979\/11240212.pdf?arnumber=11240212","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T22:00:28Z","timestamp":1768255228000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11240212\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":43,"URL":"https:\/\/doi.org\/10.1109\/tcomm.2025.3631558","relation":{},"ISSN":["0090-6778","1558-0857"],"issn-type":[{"value":"0090-6778","type":"print"},{"value":"1558-0857","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}