Deep Reinforcement Learning for Blind Passive Beamforming in RIS-Assisted MIMO Systems
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
- The Gaussian Multiuser Channel Capacity Region
- The mathematical landscape of partial information decomposition: A comprehensive review of properties and measures
- Electromagnetic Signal and Information Theory: A Continuous-Aperture Array Perspective
- Analytically Characterized Optimal Power Control for Signal-Level-Integrated Sensing, Computing and Communication in Federated Learning
- Information Spectrum Methods for Multiple-Access Channels--Part I: epsilon-Capacity Regions in the Mixed Gaussian Case
- Seed Recycling: Explicit Codes for Mixed Synchronization Errors Matching the Leading Term of the Gilbert--Varshamov Bound