今天尝试了一下https://github.com/AI4Finance-Foundation/Deep-Reinforcement-Learning-for-Automated-Stock-Trading-Ensemble-Strategy-ICAIF-2020的股票量化交易策略,需要安装很多库,我这里把我的运行方法分享出来:
git clone https://github.com/AI4Finance-Foundation/Deep-Reinforcement-Learning-for-Automated-Stock-Trading-Ensemble-Strategy-ICAIF-2020.git
git clone https://github.com/hill-a/stable-baselines.git
cd Deep-Reinforcement-Learning-for-Automated-Stock-Trading-Ensemble-Strategy-ICAIF-2020
pip install -r requirements.txt
然后运行命令:
export PYTHONPATH=/your_path_to/stable-baselines:$PYTHONPATH
python run_DRL.py
总体上这个方法给我们提供了很多思路,比如它的多支股票的环境,可以给我们一定的启发,但是那个stable-baselines把强化学习算法的细节封装了,不太适合我们去改进和调整,我是希望能看到强化学习的建模过程的,总体上,这个算法离实用还差了那么一点。
参考文献
[1]. Deep Reinforcement Learning for Automated Stock Trading: An Ensemble Strategy. https://github.com/AI4Finance-Foundation/Deep-Reinforcement-Learning-for-Automated-Stock-Trading-Ensemble-Strategy-ICAIF-2020