Experimental code supporting the results presented in the scientific research paper:
Thibaut Théate and Damien Ernst. "An Application of Deep Reinforcement Learning to Algorithmic Trading." (2020). [arxiv]
The dependencies are listed in the text file "requirements.txt":
- Python 3.7.4
- Pytorch 1.5.0
- Tensorboard
- Gym
- Numpy
- Pandas
- Matplotlib
- Scipy
- Seaborn
- Statsmodels
- Requests
- Pandas-datareader
- TQDM
- Tabulate
Simulating (training and testing) a chosen supported algorithmic trading strategy on a chosen supported stock is performed by running the following command:
python main.py -strategy STRATEGY -stock STOCK
with:
- STRATEGY being the name of the trading strategy (by default TDQN),
- STOCK being the name of the stock (by default Apple).
The performance of this algorithmic trading policy will be automatically displayed in the terminal, and some graphs will be generated and stored in the folder named "Figures".
If you make use of this experimental code, please cite the associated research paper:
@inproceedings{Theate2020,
title={An Aplication of Deep Reinforcement Learning to Algorithmic Trading},
author={Theate, Thibaut and Ernst, Damien},
year={2020}
}