{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T05:27:14Z","timestamp":1768282034464,"version":"3.49.0"},"reference-count":53,"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":["2024YFE0200700"],"award-info":[{"award-number":["2024YFE0200700"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Natural Science Foundation on Frontier Leading Technology Basic Research Project of Jiangsu","award":["BK20222001"],"award-info":[{"award-number":["BK20222001"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U1936201"],"award-info":[{"award-number":["U1936201"]}],"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":["61971128"],"award-info":[{"award-number":["61971128"]}],"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":["62225107"],"award-info":[{"award-number":["62225107"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Jiangsu Provincial Scientific Research Center of Applied Mathematics","award":["BK20233002"],"award-info":[{"award-number":["BK20233002"]}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for Central Universities","doi-asserted-by":"publisher","award":["2242022k60002"],"award-info":[{"award-number":["2242022k60002"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Wireless Commun."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/twc.2025.3592854","type":"journal-article","created":{"date-parts":[[2025,8,4]],"date-time":"2025-08-04T18:47:07Z","timestamp":1754333227000},"page":"1767-1780","source":"Crossref","is-referenced-by-count":0,"title":["Hierarchical Reinforcement Learning-Based Beam Selection for Integrated Sensing and Communication Systems"],"prefix":"10.1109","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6119-613X","authenticated-orcid":false,"given":"Ruming","family":"Yang","sequence":"first","affiliation":[{"name":"National Mobile Communications Research Laboratory, School of Information Science and Engineering, Southeast University, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-1162-8349","authenticated-orcid":false,"given":"Xingkang","family":"Li","sequence":"additional","affiliation":[{"name":"National Mobile Communications Research Laboratory, School of Information Science and Engineering, Southeast University, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3616-4616","authenticated-orcid":false,"given":"Yongming","family":"Huang","sequence":"additional","affiliation":[{"name":"National Mobile Communications Research Laboratory, School of Information Science and Engineering, Southeast University, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1474-1806","authenticated-orcid":false,"given":"Luxi","family":"Yang","sequence":"additional","affiliation":[{"name":"National Mobile Communications Research Laboratory, School of Information Science and Engineering, Southeast University, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1059-3642","authenticated-orcid":false,"given":"Wei","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering and Telecommunications, University of New South Wales, Sydney, NSW, Australia"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2021.3122519"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2021.3077307"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TAES.2017.2651698"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2022.3156632"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2008.4408448"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2007.904812"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2020.3015735"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2021.3073140"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICC45041.2023.10279159"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2023.3235355"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2010.092810.091092"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/LWC.2021.3056702"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCCWorkshops52231.2021.9538857"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2023.3312759"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/LCOMM.2021.3140093"},{"key":"ref16","doi-asserted-by":"crossref","first-page":"504","DOI":"10.1016\/j.sigpro.2017.07.001","article-title":"GLRT detector in single frequency multi-static passive radar systems","volume":"142","author":"Chalise","year":"2018","journal-title":"Signal Process."},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2024.3383209"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2023.3252885"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TAES.2021.3061809"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2023.3329224"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2024.3350714"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2020.3019523"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2023.3344600"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2023.3306889"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2024.3395319"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2020.2985686"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2024.3374352"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2022.3223066"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2022.3142513"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2021.3049380"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2021.3087233"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICC45041.2023.10279804"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2022.3144277"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3207346"},{"key":"ref35","article-title":"Data-efficient hierarchical reinforcement learning","author":"Nachum","year":"2018","journal-title":"arXiv:1805.08296"},{"key":"ref36","first-page":"1","article-title":"Sample-efficient reinforcement learning by breaking the replay ratio barrier","volume-title":"Proc. The 11th Int. Conf. Learn. Represent.","author":"D\u2019Oro"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2020.2967181"},{"key":"ref38","volume-title":"Technical Specification Group; Radio Access Network; Evolved Universal Terrestrial Radio Access (E-UTRA); Evolved Universal Terrestrial Radio Access (E-UTRA) and Evolved Universal Terrestrial Radio Access Network (E-UTRAN); Overall Description; Release 16","year":"2022"},{"key":"ref39","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"12","author":"Sutton"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3330332"},{"issue":"1","key":"ref41","doi-asserted-by":"crossref","first-page":"181","DOI":"10.1016\/S0004-3702(99)00052-1","article-title":"Between MDPs and semi-MDPs: A framework for temporal abstraction in reinforcement learning","volume":"112","author":"Sutton","year":"1999","journal-title":"Artif. Intell."},{"key":"ref42","first-page":"393","article-title":"Reinforcement learning methods for continuous-time Markov decision problems","volume-title":"Proc. 7th Int. Conf. Neural Inf. Process. Syst.","author":"Bradtke"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10916"},{"key":"ref44","article-title":"Dota 2 with large scale deep reinforcement learning","author":"Berner","year":"2019","journal-title":"arXiv:1912.06680"},{"key":"ref45","article-title":"StarCraft II: A new challenge for reinforcement learning","author":"Vinyals","year":"2017","journal-title":"arXiv:1708.04782"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.32473\/flairs.v35i.130584"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2022.3159836"},{"key":"ref48","article-title":"Playing Atari with deep reinforcement learning","author":"Mnih","year":"2013","journal-title":"arXiv:1312.5602"},{"key":"ref49","first-page":"1995","article-title":"Dueling network architectures for deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wang"},{"key":"ref50","volume-title":"On-Line Q-Learning Using Connectionist Systems","volume":"37","author":"Rummery","year":"1994"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00925"},{"key":"ref52","article-title":"Continuous control with deep reinforcement learning","author":"Lillicrap","year":"2015","journal-title":"arXiv:1509.02971"},{"key":"ref53","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Fujimoto"}],"container-title":["IEEE Transactions on Wireless Communications"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7693\/11298242\/11107326.pdf?arnumber=11107326","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T22:06:18Z","timestamp":1768255578000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11107326\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":53,"URL":"https:\/\/doi.org\/10.1109\/twc.2025.3592854","relation":{},"ISSN":["1536-1276","1558-2248"],"issn-type":[{"value":"1536-1276","type":"print"},{"value":"1558-2248","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}