Deep Q-learning for playing Flappy Bird

python source code for training an agent to play flappy bird. It could be seen as a very basic example of Reinforcement Learning's application.


How to use

With my code, you can:

  • Train your model from scratch by running python
  • Test your trained model by running python

Trained models

You could find my trained model at trained_models/flappy_bird


  • python 3.6
  • pygame
  • cv2
  • pytorch
  • numpy