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

TL;DR

This paper introduces a Q-Learning based method for adaptively configuring RIS elements in wireless communications without requiring channel state information, aiming to reduce configuration testing and improve data transmission.

Contribution

It presents a novel approach using Q-Learning to efficiently adapt RIS configurations without CSI, minimizing the number of tests needed for optimal setup.

Findings

Q-Learning effectively reduces RIS configuration testing.

The method improves data transmission rates in RIS-aided systems.

The approach adapts to changing wireless environments without CSI.

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.