TensorFlow implementation of DQN for FlappyBird
Switch branches/tags
Nothing to show
Clone or download
Permalink
Failed to load latest commit information.
assets initial commit Sep 8, 2017
game initial commit Sep 8, 2017
logdir fixed Run mode. 1M step model Sep 15, 2017
.gitignore initial commit Sep 8, 2017
LICENSE Initial commit Sep 8, 2017
README.md initial commit Sep 8, 2017
animation1.gif initial commit Sep 8, 2017
ops.py initial commit Sep 8, 2017
qlearn.py fixed Run mode. 1M step model Sep 15, 2017

README.md

TensorFlow-FlappyBird

A TensorFlow implementation of DQN for FlappyBird. The code originally came from Keras-FlappyBird and has be adapted to now strictly use TensorFlow.

Please read the orinal author's blog post for details and check out the original repository for the inspiration behind this repo.

Installation Dependencies:

  • Python 2.7
  • Keras 2.0
  • pygame
  • scikit-image
  • TensorFlow >= 1.2

How to Run?

Inference

python qlearn.py -m "Run"

Training

If you want to train the network from beginning, delete the logdir and run

python qlearn.py -m "Train"