{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,21]],"date-time":"2026-02-21T20:28:12Z","timestamp":1771705692821,"version":"3.50.1"},"reference-count":49,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","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":[{"name":"National Key Research and Development Program of China","award":["2022YFC2405003"],"award-info":[{"award-number":["2022YFC2405003"]}]},{"name":"PNRR Project FAIR-Future AI Research","award":["PE00000013"],"award-info":[{"award-number":["PE00000013"]}]},{"name":"Spoke 9-Green-Aware AI"},{"DOI":"10.13039\/100031478","name":"NextGenerationEU","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100031478","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Veh. Technol."],"published-print":{"date-parts":[[2025,4]]},"DOI":"10.1109\/tvt.2024.3511595","type":"journal-article","created":{"date-parts":[[2024,12,5]],"date-time":"2024-12-05T19:03:49Z","timestamp":1733425429000},"page":"6433-6443","source":"Crossref","is-referenced-by-count":2,"title":["Recurrent Flash Reinforcement Learning for Dynamic Spectrum Access and Power Control"],"prefix":"10.1109","volume":"74","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9529-4317","authenticated-orcid":false,"given":"Kai","family":"Lin","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, Dalian University of Technology, Dalian, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-9381-2901","authenticated-orcid":false,"given":"Hanjie","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Dalian University of Technology, Dalian, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7756-4061","authenticated-orcid":false,"given":"Tao","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Dalian University of Technology, Dalian, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4159-2765","authenticated-orcid":false,"given":"Pasquale","family":"Pace","sequence":"additional","affiliation":[{"name":"Department of Informatics, Modeling, Electronics and System Engineering, University of Calabria, Rende, Italy"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4039-891X","authenticated-orcid":false,"given":"Giancarlo","family":"Fortino","sequence":"additional","affiliation":[{"name":"Department of Informatics, Modeling, Electronics and System Engineering, University of Calabria, Rende, Italy"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.comnet.2006.05.001"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MSPEC.2004.1270548"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2017.2774240"},{"key":"ref4","article-title":"Report of the spectrum efficiency working group","year":"2002"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2012.050112.110152"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1017\/dap.2020.6"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2019.2901471"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1049\/cmu2.12468"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2023.3236035"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.23919\/JCC.2019.12.002"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.3390\/s23167144"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICNC47757.2020.9049731"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1002\/ett.4388"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2019.2891291"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2022.3160197"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.3390\/s23052622"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.adhoc.2023.103257"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2018.2872441"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.3390\/math11163437"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2022.3198665"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2022.3165819"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.3390\/s151128889"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1063\/1.5004967"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2023.3242727"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/s11277-021-09156-x"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.dcan.2022.03.002"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.03.054"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.comnet.2023.109989"},{"key":"ref29","article-title":"HyAR: Addressing discrete-continuous action reinforcement learning via hybrid action representation","author":"Li","year":"2022"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.35833\/MPCE.2021.000394"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2022.3166110"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1186\/s13638-022-02124-4"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/dasc52595.2021.9594421"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref35","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","author":"Chung","year":"2014"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref37","article-title":"Deep reinforcement learning with relational inductive biases","volume-title":"Proc. 7th Int. Conf. Learn. Representations","author":"Zambaldi","year":"2019"},{"key":"ref38","first-page":"22574","article-title":"The sensory neuron as a transformer: Permutation-invariant neural networks for reinforcement learning","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Tang","year":"2021"},{"key":"ref39","first-page":"15340","article-title":"Transformers are meta-reinforcement learners","volume-title":"Proc. 39th Int. Conf. Mach. Learn.","volume":"162","author":"Melo","year":"2022"},{"key":"ref40","first-page":"39","article-title":"WINNER II channel models","volume-title":"Radio Technologies and Concepts for IMT-Advanced","year":"2010"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/584091.584093"},{"key":"ref42","first-page":"11079","article-title":"Recurrent memory transformer","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Bulatov","year":"2022"},{"key":"ref43","first-page":"9099","article-title":"Transformer quality in linear time","volume-title":"Proc. 39th Int. Conf. Mach. Learn.","volume":"162","author":"Hua","year":"2022"},{"key":"ref44","article-title":"Playing Atari with deep reinforcement learning","author":"Mnih","year":"2013"},{"key":"ref45","article-title":"Continuous control with deep reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Lillicrap","year":"2016"},{"key":"ref46","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"ref47","article-title":"V-MPO: On-policy maximum a posteriori policy optimization for discrete and continuous control","author":"Song","year":"2019"},{"key":"ref48","first-page":"1889","article-title":"Trust region policy optimization","volume-title":"Proc. 32nd Int. Conf. Mach. Learn.","volume":"37","author":"Schulman","year":"2015"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/VETECS.2011.5956333"}],"container-title":["IEEE Transactions on Vehicular Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/25\/10969493\/10778565.pdf?arnumber=10778565","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,19]],"date-time":"2025-04-19T04:28:30Z","timestamp":1745036910000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10778565\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4]]},"references-count":49,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tvt.2024.3511595","relation":{},"ISSN":["0018-9545","1939-9359"],"issn-type":[{"value":"0018-9545","type":"print"},{"value":"1939-9359","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4]]}}}