On the Robustness of Deep Reinforcement Learning in IRS-Aided Wireless Communications Systems
This work addresses robustness challenges in IRS-aided wireless communications for improved signal quality, but it appears incremental as it compares existing methods without introducing a new paradigm.
The paper tackled the problem of optimizing phase shifts in an Intelligent Reflecting Surface-aided wireless system to maximize signal-to-noise ratio, finding that Deep Reinforcement Learning solutions demonstrated greater robustness to noisy channels and user mobility compared to conventional methods.
We consider an Intelligent Reflecting Surface (IRS)-aided multiple-input single-output (MISO) system for downlink transmission. We compare the performance of Deep Reinforcement Learning (DRL) and conventional optimization methods in finding optimal phase shifts of the IRS elements to maximize the user signal-to-noise (SNR) ratio. Furthermore, we evaluate the robustness of these methods to channel impairments and changes in the system. We demonstrate numerically that DRL solutions show more robustness to noisy channels and user mobility.