Welcome to the "RL for Atom Cooling" repository. This repository contains three data files: environmental parameters, actions (control parameters), and atom numbers (on a logarithmic scale).
Additionally, we offer a straightforward sample script written in Python using TensorFlow's Keras library. This script demonstrates an example of how one may train an RL agent offline for subsequent online training. For simplicity, the provided Python file is a self-contained script. After downloading both the script and data files, you'll only need to modify the file paths in the code to match your local directory.
For more detailed insights and information, please refer to the accompanying manuscript https://arxiv.org/abs/2308.05216