English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Millimeter wave (mmWave) beam-tracking based on machine learning enables thedevelopment of accurate tracking policies while obviating the need toperiodically solve beam-optimization problems. However, its applicability isstill arguable when training-test gaps exist in terms of environmentalparameters that affect the node dynamics. From this skeptical point of view,the contribution of this study is twofold. First, by considering an examplescenario, we confirm that the training-test gap adversely affects thebeam-tracking performance. More specifically, we consider nodes placed onoverhead messenger wires, where the node dynamics are affected by severalenvironmental parameters, e.g, the wire mass and tension. Although these areparticular scenarios, they yield insight into the validation of thetraining-test gap problems. Second, we demonstrate the feasibility of\textit{zero-shot adaptation} as a solution, where a learning agent adapts toenvironmental parameters unseen during training. This is achieved by leveraginga robust adversarial reinforcement learning (RARL) technique, where suchtraining-and-test gaps are regarded as disturbances by adversaries that arejointly trained with a legitimate beam-tracking agent. Numerical evaluationsdemonstrate that the beam-tracking policy learned via RARL can be applied to awide range of environmental parameters without severely degrading the receivedpower.

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