• Stars
    star
    3,981
  • Rank 10,957 (Top 0.3 %)
  • Language
    JavaScript
  • License
    MIT License
  • Created over 8 years ago
  • Updated 12 months ago

Reviews

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Repository Details

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

Flappy Learning (Demo)

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

alt tag

NeuroEvolution.js : Utilization

// 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], <score = 0>);

You can see the NeuroEvolution integration in Flappy Bird in Game.js.