https://github.com/xviniette/flappylearning

Program learning to play Flappy Bird by machine learning (Neuroevolution)
https://github.com/xviniette/flappylearning

flappybird machine-learning neuroevolution

Last synced: 5 days ago
JSON representation

Program learning to play Flappy Bird by machine learning (Neuroevolution)

• Host: GitHub
• URL: https://github.com/xviniette/flappylearning
• Owner: xviniette
• License: mit
• Created: 2016-07-24T20:54:21.000Z (over 8 years ago)
• Default Branch: gh-pages
• Last Pushed: 2023-11-23T01:04:40.000Z (about 1 year ago)
• Last Synced: 2024-10-29T15:35:10.786Z (2 months ago)
• Topics: flappybird, machine-learning, neuroevolution
• Language: JavaScript
• Homepage: http://xviniette.github.io/FlappyLearning/
• Size: 10.9 MB
• Stars: 3,993
• Watchers: 116
• Forks: 498
• Open Issues: 13
• Metadata Files:
  • Readme: README.md
  • License: License

Awesome Lists containing this project

README

        
# Flappy Learning ([Demo](http://xviniette.github.io/FlappyLearning/))

Program that learns to play Flappy Bird by machine learning ([Neuroevolution](http://www.scholarpedia.org/article/Neuroevolution))

![alt tag](https://github.com/xviniette/FlappyLearning/blob/gh-pages/img/flappy.png?raw=true)

### [NeuroEvolution.js](http://github.com/xviniette/FlappyLearning/blob/gh-pages/Neuroevolution.js) : Utilization

```javascript

// Initialize

var ne = new Neuroevolution({options});

//Default options values

var options = {

    network:[1, [1], 1],    // Perceptron structure

    population:50,          // Population by generation

    elitism:0.2,            // Best networks kepts unchanged for the next generation (rate)

    randomBehaviour:0.2,    // New random networks for the next generation (rate)

    mutationRate:0.1,       // Mutation rate on the weights of synapses

    mutationRange:0.5,      // Interval of the mutation changes on the synapse weight

    historic:0,             // Latest generations saved

    lowHistoric:false,      // Only save score (not the network)

    scoreSort:-1,           // Sort order (-1 = desc, 1 = asc)

    nbChild:1               // number of child by breeding

}

//Update options at any time

ne.set({options});

// Generate first or next generation

var generation = ne.nextGeneration();

//When an network is over -> save this score

ne.networkScore(generation[x], );

```

You can see the NeuroEvolution integration in Flappy Bird in [Game.js](http://github.com/xviniette/FlappyLearning/blob/gh-pages/game.js).