Adaptive Passive Beamforming in RIS-Aided Communications With Q-Learning

Thomas Chêne; Oumaïma Bounhar; Ghaya Rekaya-Ben Othman; Oussama Damen

Adaptive Passive Beamforming in RIS-Aided Communications With Q-Learning

Information Theory 2025-05-06 v1 Signal Processing math.IT

Authors: Thomas Chêne , Oumaïma Bounhar , Ghaya Rekaya-Ben Othman , Oussama Damen

Abstract

Reconfigurable Intelligent Surfaces (RIS) appear as a promising solution to combat wireless channel fading and interferences. However, the elements of the RIS need to be properly oriented to boost the data transmission rate. In this work, we propose a new strategy to adaptively configure the RIS without Channel State Information (CSI). Our goal is to minimize the number of RIS configurations to be tested to find the optimal one. We formulate the problem as a stochastic shortest path problem, and use Q-Learning to solve it.

Keywords

reconfigurable intelligent surface beamforming wireless communication

Cite

@article{arxiv.2505.01478,
  title  = {Adaptive Passive Beamforming in RIS-Aided Communications With Q-Learning},
  author = {Thomas Chêne and Oumaïma Bounhar and Ghaya Rekaya-Ben Othman and Oussama Damen},
  journal= {arXiv preprint arXiv:2505.01478},
  year   = {2025}
}

Related papers

View all related →

Signal Processing · Electrical Eng. & Systems

Passive Beamforming For Practical RIS-Assisted Communication Systems With Non-Ideal Hardware