Reproduce “Adaptive Design of mmWave Initial Access Codebooks using Reinforcement Learning” on OpenResearch

Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.

Universal app for Apple silicon and Intel. Requires macOS 11 or later.

About this paper

Sabrine Aroua, Christos Anastasios Bovolis, Bo Göransson, Anastasios Giovanidis, Mathieu Leconte, Apostolos Destounis

The authors propose a reinforcement-learning method that selects combinations of expert-designed beams using connection feedback, without changing beam patterns. In simulation at 400 m inter-site distance, it connected an average 0.624 of user equipment, versus 0.604 for Max of Experts and 0.587 for greedy selection. This indicates higher average coverage in this simulated setting, not a deployment guarantee.

Summary by alphaXiv.

Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.