Zero-Shot Adaptation for mmWave Beam-Tracking on Overhead Messenger Wires through Robust Adversarial Reinforcement Learning

TL;DR

This paper investigates the challenges of mmWave beam-tracking when environmental parameters differ between training and deployment, and proposes a robust adversarial reinforcement learning approach for zero-shot adaptation to unseen conditions.

Contribution

It demonstrates the adverse effects of training-test gaps on beam-tracking and introduces a robust adversarial RL method enabling zero-shot adaptation to unseen environmental parameters.

Findings

Training-test gaps reduce beam-tracking performance.

RARL enables adaptation to unseen environmental parameters.

Beam-tracking policy remains effective across diverse conditions.

Abstract

Millimeter wave (mmWave) beam-tracking based on machine learning enables the development of accurate tracking policies while obviating the need to periodically solve beam-optimization problems. However, its applicability is still arguable when training-test gaps exist in terms of environmental parameters that affect the node dynamics. From this skeptical point of view, the contribution of this study is twofold. First, by considering an example scenario, we confirm that the training-test gap adversely affects the beam-tracking performance. More specifically, we consider nodes placed on overhead messenger wires, where the node dynamics are affected by several environmental parameters, e.g, the wire mass and tension. Although these are particular scenarios, they yield insight into the validation of the training-test gap problems. Second, we demonstrate the feasibility of \textit{zero-shot adaptation} as a solution, where a learning agent adapts to environmental parameters unseen during training. This is achieved by leveraging a robust adversarial reinforcement learning (RARL) technique, where such training-and-test gaps are regarded as disturbances by adversaries that are jointly trained with a legitimate beam-tracking agent. Numerical evaluations demonstrate that the beam-tracking policy learned via RARL can be applied to a wide range of environmental parameters without severely degrading the received power.