https://github.com/vivek3141/flappy-neat
Implementing the NEAT algorithm to play flappy bird
https://github.com/vivek3141/flappy-neat
flappy-bird machine-learning neat neural-network neuroevolution
Last synced: 7 months ago
JSON representation
Implementing the NEAT algorithm to play flappy bird
- Host: GitHub
- URL: https://github.com/vivek3141/flappy-neat
- Owner: vivek3141
- Created: 2018-08-04T01:53:49.000Z (about 7 years ago)
- Default Branch: master
- Last Pushed: 2018-09-03T18:18:57.000Z (about 7 years ago)
- Last Synced: 2023-03-02T04:25:48.879Z (over 2 years ago)
- Topics: flappy-bird, machine-learning, neat, neural-network, neuroevolution
- Language: Python
- Size: 669 KB
- Stars: 11
- Watchers: 1
- Forks: 1
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Flappy NEAT
This program trains an AI to play Flappy Bird using the NEAT algorithm.
## Requirements
* neat-python
* pygame
* pickle
## How it works
This program uses the Neuro Evolution of Augmenting Topologies algorithm. Unlike standard
neuroevolution, which has a fixed network structure, NEAT learns the best architecture.
## Usage
To train, run
`python3 main.py train`
To run, run
`python3 main.py run`
## Score
I got a score of 123. Feel free to change the variables in the config file and try!
## Credits
@GianottiGustavo for the game and config.