Awesome Open Source
Awesome Open Source

Playing trading games with deep reinforcement learning

This repo is the code for this paper. Deep reinforcement learing is used to find optimal strategies in these two scenarios:

  • Momentum trading: capture the underlying dynamics
  • Arbitrage trading: utilize the hidden relation among the inputs

Several neural networks are compared:

  • Recurrent Neural Networks (GRU/LSTM)
  • Convolutional Neural Network (CNN)
  • Multi-Layer Perception (MLP)


You can get all dependencies via the Anaconda environment file, env.yml:

conda env create -f env.yml

Play with it

Just call the main function


You can play with model parameters (specified in, if you get good results or any trouble, please contact me at [email protected]

Get A Weekly Email With Trending Projects For These Topics
No Spam. Unsubscribe easily at any time.
Python (1,123,251
Machine Learning (29,964
Deep Learning (22,240
Neural Network (8,373
Reinforcement Learning (3,769
Time Series (1,877
Trading (1,425
Stock (1,271
Deep Reinforcement Learning (1,007
Stock Market (889
Q Learning (472
Dqn (434
Quantitative Trading (136
Related Projects