Online Learning-based Adaptive Beam Switching for 6G Networks: Enhancing Efficiency and Resilience

Adaptive beam switching in 6G networks is challenged by high frequencies, mobility, and blockage. We propose an Online Learning framework using Deep Reinforcement Learning (DRL) with an enhanced state representation (velocity and blockage history), a GRU architecture, and prioritized experience replay for real-time beam optimization. Validated via Nvidia Sionna under time-correlated blockage, our approach significantly enhances resilience in SNR, throughput, and accuracy compared to a conventional heuristic. Furthermore, the enhanced DRL agent outperforms a reactive Multi-Armed Bandit (MAB) baseline by leveraging temporal dependencies, achieving lower performance variability. This demonstrates the benefits of memory and prioritized learning for robust 6G beam management, while confirming MAB as a strong baseline.