Hybrid Beamforming for mmWave MU-MISO Systems Exploiting Multi-agent Deep Reinforcement Learning

TL;DR

This paper introduces a multi-agent deep reinforcement learning approach for hybrid beamforming in mmWave MU-MISO systems, significantly improving spectral efficiency and reducing convergence time compared to existing methods.

Contribution

It proposes a novel multi-agent DRL framework with prioritized replay and enhanced rewards for efficient hybrid beamforming in mmWave systems.

Findings

Achieves higher spectral efficiency than benchmarks

Reduces convergence time in training

Demonstrates practical applicability of the method

Abstract

In this letter, we investigate the hybrid beamforming based on deep reinforcement learning (DRL) for millimeter Wave (mmWave) multi-user (MU) multiple-input-single-output (MISO) system. A multi-agent DRL method is proposed to solve the exploration efficiency problem in DRL. In the proposed method, prioritized replay buffer and more informative reward are applied to accelerate the convergence. Simulation results show that the proposed architecture achieves higher spectral efficiency and less time consumption than the benchmarks, thus is more suitable for practical applications.