This repository contains the implementation of the paper: High-fidelity data-driven dynamics model
for reinforcement learning-based control in HL-3 tokamak.
Note that this is a research project and by definition is unstable.
Please write to us if you find something not correct or strange.
We are sharing the codes under the condition that reproducing full or part of codes must cite the following papers.
The dependencies and required packages for running this code are listed in the requirements.txt. You can install them using pip:
pip install -r requirements.txtIf you would like to use these codes, please cite the following paper:
@article{wu2025high,
title={High-fidelity data-driven dynamics model for reinforcement learning-based control in HL-3 tokamak},
author={Wu, Niannian and Yang, Zongyu and Li, Rongpeng and Wei, Ning and Chen, Yihang and Dong, Qianyun and Li, Jiyuan and Zheng, Guohui and Gong, Xinwen and Gao, Feng and others},
journal={Communications Physics},
volume={8},
number={1},
pages={393},
year={2025},
publisher={Nature Publishing Group UK London}
}