{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T10:23:21Z","timestamp":1775557401164,"version":"3.50.1"},"reference-count":39,"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":["62201121"],"award-info":[{"award-number":["62201121"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"fellowship of China National Postdoctoral Program for Innovative Talents","award":["BX20230057"],"award-info":[{"award-number":["BX20230057"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Cogn. Commun. Netw."],"published-print":{"date-parts":[[2025,4]]},"DOI":"10.1109\/tccn.2024.3457525","type":"journal-article","created":{"date-parts":[[2024,9,10]],"date-time":"2024-09-10T15:25:03Z","timestamp":1725981903000},"page":"1316-1331","source":"Crossref","is-referenced-by-count":1,"title":["Online Learning-Based Joint Gateway Selection and User Scheduling in Non-Stationary Air-Ground Networks"],"prefix":"10.1109","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8647-4490","authenticated-orcid":false,"given":"Youkun","family":"Peng","sequence":"first","affiliation":[{"name":"National Key Laboratory of Wireless Communications, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2512-2392","authenticated-orcid":false,"given":"Gang","family":"Feng","sequence":"additional","affiliation":[{"name":"National Key Laboratory of Wireless Communications, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9264-6850","authenticated-orcid":false,"given":"Shuang","family":"Qin","sequence":"additional","affiliation":[{"name":"National Key Laboratory of Wireless Communications, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1276-0221","authenticated-orcid":false,"given":"Fengsheng","family":"Wei","sequence":"additional","affiliation":[{"name":"National Key Laboratory of Wireless Communications, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3659-3405","authenticated-orcid":false,"given":"Long","family":"Zhang","sequence":"additional","affiliation":[{"name":"Sichuan Energy Internet Research Institute, Tsinghua University, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2018.2841996"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.2018.1800160"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/VTCSpring.2019.8746478"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICC40277.2020.9149175"},{"key":"ref5","article-title":"Deep reinforcement learning amidst lifelong non-stationarity","author":"Xie","year":"2020","journal-title":"arXiv:2006.10701"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2017.2789293"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2020.2980911"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2021.3058236"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2020.3029143"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICC45855.2022.9838681"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2019.2935201"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2021.3075860"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2021.3116953"},{"key":"ref14","article-title":"Learning to adapt in dynamic, real-world environments through Meta-reinforcement learning","author":"Nagabandi","year":"2019","journal-title":"arXiv:1803.11347"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/S1364-6613(99)01294-2"},{"key":"ref16","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":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2022.3146439"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2024.3397007"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.13673"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICC42927.2021.9500646"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2022.3143372"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2021.3126825"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/LWC.2014.2342736"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2008.920143"},{"key":"ref25","article-title":"Reinforcement learning and control as probabilistic inference: Tutorial and review","author":"Levine","year":"2018","journal-title":"arXiv:1805.00909"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2889774"},{"key":"ref27","article-title":"Deep latent variable models for sequential data","author":"Fraccaro","year":"2018"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1312.6114"},{"key":"ref29","first-page":"5331","article-title":"Efficient off-policy meta-reinforcement learning via probabilistic context variables","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Rakelly"},{"key":"ref30","article-title":"Soft actor-critic for discrete action settings","author":"Christodoulou","year":"2019","journal-title":"arXiv:1910.07207"},{"key":"ref31","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Fujimoto"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1812.05905"},{"key":"ref33","article-title":"Target entropy annealing for discrete soft actor-critic","author":"Xu","year":"2021","journal-title":"arXiv:2112.02852"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2021.3123500"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i11.17136"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2016.7510820"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2017.2751045"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2023.3344519"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2023.3262826"}],"container-title":["IEEE Transactions on Cognitive Communications and Networking"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6687307\/10957747\/10673897.pdf?arnumber=10673897","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T18:41:53Z","timestamp":1762368113000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10673897\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4]]},"references-count":39,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tccn.2024.3457525","relation":{},"ISSN":["2332-7731","2372-2045"],"issn-type":[{"value":"2332-7731","type":"electronic"},{"value":"2372-2045","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4]]}}}