{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,18]],"date-time":"2026-04-18T03:06:13Z","timestamp":1776481573463,"version":"3.51.2"},"reference-count":44,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","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:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"6G Flagship","award":["369116"],"award-info":[{"award-number":["369116"]}]},{"DOI":"10.13039\/501100002341","name":"Research Council of Finland","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002341","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Mobile Comput."],"published-print":{"date-parts":[[2026,1]]},"DOI":"10.1109\/tmc.2025.3599918","type":"journal-article","created":{"date-parts":[[2025,8,19]],"date-time":"2025-08-19T18:17:54Z","timestamp":1755627474000},"page":"1137-1150","source":"Crossref","is-referenced-by-count":3,"title":["An Offline Multi-Agent Reinforcement Learning Framework for Radio Resource Management"],"prefix":"10.1109","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6322-2036","authenticated-orcid":false,"given":"Eslam","family":"Eldeeb","sequence":"first","affiliation":[{"name":"Centre for Wireless Communications (CWC), University of Oulu, Oulu, Finland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8689-5313","authenticated-orcid":false,"given":"Hirley","family":"Alves","sequence":"additional","affiliation":[{"name":"Centre for Wireless Communications (CWC), University of Oulu, Oulu, Finland"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2019.2916583"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1186\/s13638-021-02010-5"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2023.3300664"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2022.3195067"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2016.2550765"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ACSSC.2015.7421354"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2008.070227"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.2014.6845058"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.004.2200532"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2020.3036871"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/iotm.001.2400093"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-022-04105-y"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0172395"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2023.3339514"},{"key":"ref16","volume-title":"Multi-Agent Reinforcement Learning: Foundations and Modern Approaches","author":"Albrecht","year":"2024"},{"key":"ref17","article-title":"Value-decomposition networks for cooperative multi-agent learning","author":"Sunehag","year":"2017"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2023.3250495"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2023.3312276"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2019.2928811"},{"key":"ref21","article-title":"Offline reinforcement learning: Tutorial, review, and perspectives on open problems","author":"Levine","year":"2020"},{"key":"ref22","article-title":"Offline reinforcement learning with implicit Q-learning","author":"Kostrikov","year":"2021"},{"key":"ref23","first-page":"1889","article-title":"Trust region policy optimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Schulman"},{"key":"ref24","first-page":"1179","article-title":"Conservative Q-learning for offline reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kumar"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2013.060513.120959"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2831240"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2022.3222092"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2019.2959185"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2023.3255547"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/PIMRC56721.2023.10293964"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2021.3051163"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2019.2933973"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2020.3029609"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2022.3207918"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/tccn.2024.3499357"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2024.3395624"},{"key":"ref37","article-title":"Offline and distributional reinforcement learning for radio resource management","author":"Eldeeb","year":"2024"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-022-1383-7"},{"key":"ref39","article-title":"Simulation assumptions and parameters for FDD HeNB RF requirements","year":"2009"},{"key":"ref40","article-title":"NR; Physical Layer Measurements","year":"2021"},{"key":"ref41","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proc. 35th Int. Conf. Mach. Learn.","author":"Haarnoja"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i13.17353"},{"key":"ref43","first-page":"2052","article-title":"Off-policy deep reinforcement learning without exploration","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","author":"Fujimoto"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ISIT.2014.6875098"}],"container-title":["IEEE Transactions on Mobile Computing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7755\/11275706\/11129914.pdf?arnumber=11129914","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,4]],"date-time":"2025-12-04T18:39:25Z","timestamp":1764873565000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11129914\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1]]},"references-count":44,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tmc.2025.3599918","relation":{},"ISSN":["1536-1233","1558-0660","2161-9875"],"issn-type":[{"value":"1536-1233","type":"print"},{"value":"1558-0660","type":"electronic"},{"value":"2161-9875","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1]]}}}