https://github.com/snowkylin/rl-flappybird

Using deep reinforcement learning to play flappy bird. Implemented by TensorFlow.
https://github.com/snowkylin/rl-flappybird

deep-reinforcement-learning flappy-bird q-learning tensorflow

Last synced: about 1 year ago
JSON representation

Using deep reinforcement learning to play flappy bird. Implemented by TensorFlow.

• Host: GitHub
• URL: https://github.com/snowkylin/rl-flappybird
• Owner: snowkylin
• Created: 2017-01-19T17:03:07.000Z (over 9 years ago)
• Default Branch: master
• Last Pushed: 2017-01-20T12:01:54.000Z (over 9 years ago)
• Last Synced: 2025-04-13T01:07:30.016Z (about 1 year ago)
• Topics: deep-reinforcement-learning, flappy-bird, q-learning, tensorflow
• Language: Python
• Size: 45.6 MB
• Stars: 2
• Watchers: 2
• Forks: 4
• Open Issues: 0
• Metadata Files:
  • Readme: readme.md

Awesome Lists containing this project

README

          
# Play Flappy Bird with TensorFlow 

## Demo

[![Play Flappy Bird with TensorFlow ](https://img.youtube.com/vi/nwp685pnDNg/0.jpg)](https://www.youtube.com/watch?v=nwp685pnDNg)

## Dependencies

* Python

* TensorFlow

* pygame

* OpenCV-Python

## Usage

Run `play.py` to play flappy bird by trained network.

Run `train.py` to train the network on your computer.

## Credit

This work is highly based on [yenchenlin/DeepLearningFlappyBird](https://github.com/yenchenlin/DeepLearningFlappyBird)