{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T15:53:01Z","timestamp":1784217181361,"version":"3.55.0"},"reference-count":39,"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":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62394292"],"award-info":[{"award-number":["62394292"]}],"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":["U20A20158"],"award-info":[{"award-number":["U20A20158"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100006579","name":"Ministry of Industry and Information Technology of the People's Republic of China","doi-asserted-by":"publisher","award":["TC220H07E"],"award-info":[{"award-number":["TC220H07E"]}],"id":[{"id":"10.13039\/501100006579","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Zhejiang Provincial Key Research and Development Program","award":["2023C01021"],"award-info":[{"award-number":["2023C01021"]}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["226-2024-00069"],"award-info":[{"award-number":["226-2024-00069"]}],"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":[[2025,4]]},"DOI":"10.1109\/twc.2024.3524305","type":"journal-article","created":{"date-parts":[[2025,1,8]],"date-time":"2025-01-08T20:39:34Z","timestamp":1736368774000},"page":"2750-2765","source":"Crossref","is-referenced-by-count":2,"title":["Efficient Initial Access Based on DRL-Empowered Beam Sweeping"],"prefix":"10.1109","volume":"24","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6286-9399","authenticated-orcid":false,"given":"Jingze","family":"Che","sequence":"first","affiliation":[{"name":"College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2346-6228","authenticated-orcid":false,"given":"Zhaoyang","family":"Zhang","sequence":"additional","affiliation":[{"name":"College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2454-1904","authenticated-orcid":false,"given":"Yuzhi","family":"Yang","sequence":"additional","affiliation":[{"name":"Institute of Fundamental and Transdisciplinary Research, Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4475-589X","authenticated-orcid":false,"given":"Zhaohui","family":"Yang","sequence":"additional","affiliation":[{"name":"College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/GLOBECOM54140.2023.10437816"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2022.3143241"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/WCNC51071.2022.9771993"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2020.2965926"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2018.2869411"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.001.2001184"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.004.2200462"},{"key":"ref8","volume-title":"5G NR\u2014Physical Channels and Modulation\u2014Release 15","year":"2018"},{"key":"ref9","volume-title":"5G NR\u2014Physical Layer Procedures for Control\u2014Release 15","year":"2018"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-022-3542-6"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2021.3126856"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2021.3071836"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2022.3168878"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/VTC2020-Spring48590.2020.9128625"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2016.2520930"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2020.3019523"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2019.1800805"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1002\/ett.3683"},{"key":"ref19","article-title":"Beam training and tracking in mmWave communication: A survey","author":"Wang","year":"2022","journal-title":"arXiv:2205.10169"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2017.2725878"},{"key":"ref21","first-page":"1","article-title":"Policy gradient methods for reinforcement learning with function approximation","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurlPS)","volume":"12","author":"Sutton"},{"key":"ref22","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Mnih"},{"key":"ref23","article-title":"Continuous control with deep reinforcement learning","author":"Lillicrap","year":"2015","journal-title":"arXiv:1509.02971"},{"key":"ref24","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1503.02531"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/VTC2023-Spring57618.2023.10201005"},{"key":"ref27","article-title":"High-dimensional continuous control using generalized advantage estimation","author":"Schulman","year":"2015","journal-title":"arXiv:1506.02438"},{"key":"ref28","article-title":"DeepMIMO: A generic deep learning dataset for millimeter wave and massive MIMO applications","author":"Alkhateeb","year":"2019","journal-title":"arXiv:1902.06435"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TAP.2014.2310220"},{"key":"ref30","article-title":"QuaDRiGa-quasi deterministic radio channel generator, user manual and documentation","author":"Jaeckel","year":"2023"},{"key":"ref31","volume-title":"5G NR\u2014Study on Channel Model for Frequencies From 0.5G To 100 GHz\u2014Release 17","year":"2022"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ITA.2017.8023448"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2005.12729"},{"key":"ref34","article-title":"What matters in on-policy reinforcement learning? A large-scale empirical study","author":"Andrychowicz","year":"2020","journal-title":"arXiv:2006.05990"},{"key":"ref35","first-page":"5015","article-title":"The mirage of action-dependent baselines in reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Tucker"},{"key":"ref36","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Fujimoto"},{"key":"ref37","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Haarnoja"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/LWC.2021.3115030"},{"key":"ref39","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton","year":"2018"}],"container-title":["IEEE Transactions on Wireless Communications"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7693\/10960779\/10834506.pdf?arnumber=10834506","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,14]],"date-time":"2025-04-14T17:41:12Z","timestamp":1744652472000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10834506\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4]]},"references-count":39,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/twc.2024.3524305","relation":{},"ISSN":["1536-1276","1558-2248"],"issn-type":[{"value":"1536-1276","type":"print"},{"value":"1558-2248","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4]]}}}