Deep Reinforcement Learning for Blind Passive Beamforming in RIS-Assisted MIMO Systems

arXiv:2610.39827 · cs.IT, math.IT, stat.ML · Submitted 2026-10-29 · Read on arXiv

cs.IT, math.IT, stat.ML

Submitted: 2026-10-29

Updated: 2026-10-29

Comments: Accepted at AIxNET 2026. 6 pages. Copyright may be transferred to IEEE after publication, after which this version may no longer be accessible

License: http://creativecommons.org/licenses/by-nc-sa/4.0/

The gist: Reconfigurable Intelligent Surfaces (RIS) are a promising solution for improving millimeter-wave (mmWave) communications by controlling signal propagation.

Terminology

Abstract

Reconfigurable Intelligent Surfaces (RIS) are a promising solution for improving millimeter-wave (mmWave) communications by controlling signal propagation. Yet, selecting the optimal RIS configuration remains challenging due to the high-dimensional search space and signaling overhead. We propose a Deep Reinforcement Learning (DRL) framework for blind passive beamforming, where a Deep Q-Learning (DQL) agent learns an adaptive policy to select near-optimal RIS configurations while sounding only few codewords, without channel state information. Results show that our approach outperforms Q-Learning (QL) and conventional baselines in convergence, performance, and overhead reduction.

Related papers