Reinforcement Learning-Based Multi-Agent Beam Tracking for Multi-RIS Hybrid Beamforming
IEEE Transactions on Wireless Communications · 2026 · 25 · 4309-4325
DOI: 10.1109/twc.2025.3610047 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Wireless Communications, 2026. Verfasst von Najam Us Saqib und 5 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 47 Literaturangaben. Gefördert von: Institute of Information and Communications Technology Planning and Evaluation, Korean Government (Development of technology for securing and supplying radio resources and Development of upper-mid band extreme massive MIMO, National Research Foundation of Korea.
Abstract (Originalsprache)
Reconfigurable intelligent surfaces (RIS) are emerging as a promising technology for next-generation wireless communications, capable of mitigating severe propagation attenuation, enhancing spectral efficiency, and expanding signal coverage. This paper focuses on online millimeter-wave (mmWave) beam tracking for multi-RIS-assisted hybrid beamforming systems. We develop two novel beam tracking algorithms based on multi-agent deep reinforcement learning (DRL): a multi-agent deep deterministic policy gradient (MADDPG)-based algorithm for continuous-domain beam angle tracking and a multi-agent deep Q-network (MADQN)-based algorithm for codebook-based discrete-domain beam angle tracking. Both algorithms are designed to maximize the sum rate by jointly optimizing analog beamforming for the base station (BS) and reflection coefficients for multiple RISs in dynamic environments, leveraging historical information and without requiring current user position or channel information. After determining analog beamforming and RIS reflection coefficients, digital beamforming for the BS is constructed by estimating the end-to-end effective channel, which significantly reduces the overhead of channel estimation. Experimental results demonstrate that the proposed algorithms effectively adapt the analog beamformer and RIS reflection coefficients to account for user mobility, significantly outperforming existing benchmark schemes.
Förderung
- Institute of Information and Communications Technology Planning and Evaluation
- Korean Government (Development of technology for securing and supplying radio resources and Development of upper-mid band extreme massive MIMO
- National Research Foundation of Korea
- Korean Government through MSIT
- National Natural Science Foundation of China
- Zhejiang Provincial Natural Science Foundation of China
Zitieren
APA
Saqib, N. U., Zhu, G., Chae, S. H., Zhou, C., Zheng, Z., & Jeon, S. (2026). Reinforcement Learning-Based Multi-Agent Beam Tracking for Multi-RIS Hybrid Beamforming. IEEE Transactions on Wireless Communications, 25, 4309-4325. https://doi.org/10.1109/twc.2025.3610047
Vancouver
Saqib NU, Zhu G, Chae SH, Zhou C, Zheng Z, Jeon S. Reinforcement Learning-Based Multi-Agent Beam Tracking for Multi-RIS Hybrid Beamforming. IEEE Transactions on Wireless Communications. 2026;25:4309-4325. doi:10.1109/twc.2025.3610047
BibTeX
@article{Saqib2026,
author = {Saqib, Najam Us and Zhu, Guopei and Chae, Sung Ho and Zhou, Changjun and Zheng, Zhonglong and Jeon, Sang-Woon},
title = {Reinforcement Learning-Based Multi-Agent Beam Tracking for Multi-RIS Hybrid Beamforming},
journal = {IEEE Transactions on Wireless Communications},
year = {2026},
volume = {25},
pages = {4309--4325},
doi = {10.1109/twc.2025.3610047}
}
EUVIMED