Bayesian Reinforcement Learning for IRS-Assisted Massive MIMO-OFDM Channel Feedback, Beamforming, and IRS Control

In this paper, we propose a Bayesian Reinforcement Learning (BRL)-based CSI feedback, beamforming, and IRS control scheme for IRS-assisted massive MIMO-OFDM systems. Firstly, the proposed approach utilizes the equivalent CSI for optimization, aligning with current channel estimation protocols without necessitating extensive modifications. Secondly, it employs a practical IRS control model that optimizes the effective capacitance of IRS control circuits rather than IRS reflection coefficients, accurately reflecting the IRS's frequencyresponsive behavior to enhance system performance. Additionally, we advocate bypassing the reconstruction of the CSI at the BS to eliminate information irrelevant to beamforming and IRS control, thereby boosting feedback efficiency. Simulation results demonstrate that the proposed IRS-CSI-BRL scheme significantly outperforms start-of-the-art solutions in feedback overhead reduction and system data rate enhancement.