{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T05:13:35Z","timestamp":1768281215305,"version":"3.49.0"},"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\/501100010418","name":"Institute of Information and Communications Technology Planning and Evaluation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100010418","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Korean Government (Development of technology for securing and supplying radio resources and Development of upper-mid band extreme massive MIMO","award":["2021-0-00092"],"award-info":[{"award-number":["2021-0-00092"]}]},{"name":"Korean Government (Development of technology for securing and supplying radio resources and Development of upper-mid band extreme massive MIMO","award":["RS-2024-00397216"],"award-info":[{"award-number":["RS-2024-00397216"]}]},{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Korean Government through MSIT","award":["RS-2025-25456394"],"award-info":[{"award-number":["RS-2025-25456394"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62272418"],"award-info":[{"award-number":["62272418"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"Zhejiang Provincial Natural Science Foundation of China","doi-asserted-by":"publisher","award":["LD24F020004"],"award-info":[{"award-number":["LD24F020004"]}],"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":["62272419"],"award-info":[{"award-number":["62272419"]}],"id":[{"id":"10.13039\/501100001809","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.2025.3610047","type":"journal-article","created":{"date-parts":[[2025,9,22]],"date-time":"2025-09-22T17:46:20Z","timestamp":1758563180000},"page":"4309-4325","source":"Crossref","is-referenced-by-count":0,"title":["Reinforcement Learning-Based Multi-Agent Beam Tracking for Multi-RIS Hybrid Beamforming"],"prefix":"10.1109","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9149-0946","authenticated-orcid":false,"given":"Najam Us","family":"Saqib","sequence":"first","affiliation":[{"name":"Department of Electrical and Electronic Engineering, Hanyang University, Ansan, South Korea"}]},{"given":"Guopei","family":"Zhu","sequence":"additional","affiliation":[{"name":"Department of Electrical and Electronic Engineering, Hanyang University, Ansan, South Korea"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6429-1324","authenticated-orcid":false,"given":"Sung Ho","family":"Chae","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering, Kwangwoon University, Seoul, South Korea"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0129-2231","authenticated-orcid":false,"given":"Changjun","family":"Zhou","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Zhejiang Normal University, Jinhua, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5271-9215","authenticated-orcid":false,"given":"Zhonglong","family":"Zheng","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Zhejiang Normal University, Jinhua, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0199-2254","authenticated-orcid":false,"given":"Sang-Woon","family":"Jeon","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Zhejiang Normal University, Jinhua, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TAP.2017.2734243"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2015.2455980"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2016.2520912"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICTC52510.2021.9620835"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICOIN50884.2021.9334028"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2021.3071836"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2019.2958916"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.001.1900107"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2021.3127924"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2024.3387449"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2025.3552688"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2022.3157880"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCChinaW.2019.8849960"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2021.3052074"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2022.3193626"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.001.1900534"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/LCOMM.2023.3240499"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2019.2936025"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2020.3000814"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2021.3054121"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2020.3000813"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2022.3214818"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2022.3196313"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2022.3232795"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2022.3216852"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.006.2100517"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2023.3347419"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10097134"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2024.3496393"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2020.3000835"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2021.3126856"},{"key":"ref32","article-title":"Learning reflection beamforming codebooks for arbitrary RIS and non-stationary channels","author":"Zhang","year":"2021","journal-title":"arXiv:2109.14909"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2022.3200998"},{"key":"ref34","article-title":"Offline reinforcement learning: Tutorial, review, and perspectives on open problems","author":"Levine","year":"2020","journal-title":"arXiv:2005.01643"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2023.3335362"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.1987.1146527"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2023.3251374"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2021.3078502"},{"key":"ref39","first-page":"1","article-title":"Deterministic policy gradient algorithms","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Silver"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3338866"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2018.2865759"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2017.2713357"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM41043.2020.9155475"},{"key":"ref44","first-page":"1995","article-title":"Dueling network architectures for deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wang"},{"key":"ref45","volume-title":"Keras","author":"Chollet et al","year":"2015"},{"key":"ref46","volume-title":"Tensorflow: Large-Scale Machine Learning on Heterogeneous Systems","author":"Abadi et al","year":"2015"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2020.2970061"}],"container-title":["IEEE Transactions on Wireless Communications"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7693\/11298242\/11175309.pdf?arnumber=11175309","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T22:09:21Z","timestamp":1768255761000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11175309\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":47,"URL":"https:\/\/doi.org\/10.1109\/twc.2025.3610047","relation":{},"ISSN":["1536-1276","1558-2248"],"issn-type":[{"value":"1536-1276","type":"print"},{"value":"1558-2248","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}