{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,21]],"date-time":"2026-07-21T14:40:42Z","timestamp":1784644842508,"version":"3.55.0"},"reference-count":47,"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":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2025ZD1302500"],"award-info":[{"award-number":["2025ZD1302500"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100010296","name":"Natural Science Foundation on Frontier Leading Technology Basic Research Project of Jiangsu","doi-asserted-by":"publisher","award":["BK20222001"],"award-info":[{"award-number":["BK20222001"]}],"id":[{"id":"10.13039\/501100010296","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["U1936201"],"award-info":[{"award-number":["U1936201"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["61971128"],"award-info":[{"award-number":["61971128"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["U25B2007"],"award-info":[{"award-number":["U25B2007"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62225107"],"award-info":[{"award-number":["62225107"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"National Key Research and Development Program of China","award":["2024YFC3807900"],"award-info":[{"award-number":["2024YFC3807900"]}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"crossref","award":["2242022k60002"],"award-info":[{"award-number":["2242022k60002"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Postgraduate Research and Practice Innovation Program of Jiangsu Province","award":["KYCX23_0258"],"award-info":[{"award-number":["KYCX23_0258"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Wireless Commun."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/twc.2025.3650204","type":"journal-article","created":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T22:04:05Z","timestamp":1768255445000},"page":"9875-9890","source":"Crossref","is-referenced-by-count":4,"title":["Efficient Beam Selection for ISAC in Cell-Free Massive MIMO via Digital Twin-Assisted Deep Reinforcement Learning"],"prefix":"10.1109","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6945-8827","authenticated-orcid":false,"given":"Jiexin","family":"Zhang","sequence":"first","affiliation":[{"name":"National Mobile Communications Research Laboratory, Frontiers Science Center for Mobile Information Communication and Security, Southeast University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6153-0505","authenticated-orcid":false,"given":"Shu","family":"Xu","sequence":"additional","affiliation":[{"name":"School of Electronic and Optical Engineering, Nanjing University of Science and Technology, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4689-7226","authenticated-orcid":false,"given":"Chunguo","family":"Li","sequence":"additional","affiliation":[{"name":"National Mobile Communications Research Laboratory, Frontiers Science Center for Mobile Information Communication and Security, Southeast University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3616-4616","authenticated-orcid":false,"given":"Yongming","family":"Huang","sequence":"additional","affiliation":[{"name":"National Mobile Communications Research Laboratory, Frontiers Science Center for Mobile Information Communication and Security, Southeast University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1474-1806","authenticated-orcid":false,"given":"Luxi","family":"Yang","sequence":"additional","affiliation":[{"name":"National Mobile Communications Research Laboratory, Frontiers Science Center for Mobile Information Communication and Security, Southeast University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2022.3156632"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2024.3351856"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2021.3113120"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/twc.2025.3542206"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2024.3462681"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2022.3180803"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2025.3537103"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2022.3183621"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/mvt.2025.3531088"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/GCWkshps58843.2023.10465106"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2024.3383209"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2024.3392330"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2024.3490740"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2017.2655515"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/twc.2025.3553438"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2018.2869411"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/LWC.2020.2994218"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s11721-007-0002-0"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2021.3049380"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2024.3405856"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2022.3144277"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2020.3038787"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2021.3087233"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2023.3300830"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TAES.2021.3061809"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/twc.2025.3583950"},{"key":"ref27","article-title":"Offline reinforcement learning: Tutorial, review, and perspectives on open problems","author":"Levine","year":"2020","journal-title":"arXiv:2005.01643"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3250269"},{"key":"ref29","first-page":"1","article-title":"Stabilizing off-policy Q-learning via bootstrapping error reduction","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kumar"},{"key":"ref30","first-page":"1179","article-title":"Conservative Q-learning for offline reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kumar"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.001.2200866"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2024.3495212"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/WCNC57260.2024.10570512"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2024.3511705"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2024.3395698"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2019.2927312"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2023.3346457"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2025.3542399"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TAES.2012.6324717"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TAES.2007.4441739"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1975.1055327"},{"key":"ref42","first-page":"278","article-title":"Policy invariance under reward transformations: Theory and application to reward shaping","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ng"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref44","first-page":"1995","article-title":"Dueling network architectures for deep reinforcement learning","volume-title":"Proc. Int. Conf. Int. Conf. Mach. Learn.","volume":"48","author":"Wang"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2024.3451561"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1023\/A:1007678930559"}],"container-title":["IEEE Transactions on Wireless Communications"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7693\/11298242\/11345189.pdf?arnumber=11345189","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T09:18:38Z","timestamp":1768295918000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11345189\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":47,"URL":"https:\/\/doi.org\/10.1109\/twc.2025.3650204","relation":{},"ISSN":["1536-1276","1558-2248"],"issn-type":[{"value":"1536-1276","type":"print"},{"value":"1558-2248","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}