All Projects → xviniette → Flappylearning

xviniette / Flappylearning

Licence: mit
Program learning to play Flappy Bird by machine learning (Neuroevolution)

Programming Languages

javascript
184084 projects - #8 most used programming language
HTML
75241 projects

Projects that are alternatives of or similar to Flappylearning

Machine Learning Flappy Bird
Machine Learning for Flappy Bird using Neural Network and Genetic Algorithm
Stars: ✭ 1,683 (-56.72%)
Mutual labels:  neuroevolution, flappybird
Flappy-Bird-Genetic-Algorithms
Use genetic algorithms to train flappy bird
Stars: ✭ 83 (-97.87%)
Mutual labels:  flappybird
neat-python
Python implementation of the NEAT neuroevolution algorithm
Stars: ✭ 32 (-99.18%)
Mutual labels:  neuroevolution
neat-openai-gym
NEAT for Reinforcement Learning on the OpenAI Gym
Stars: ✭ 19 (-99.51%)
Mutual labels:  neuroevolution
neuro-evolution
A project on improving Neural Networks performance by using Genetic Algorithms.
Stars: ✭ 25 (-99.36%)
Mutual labels:  neuroevolution
es pytorch
High performance implementation of Deep neuroevolution in pytorch using mpi4py. Intended for use on HPC clusters
Stars: ✭ 20 (-99.49%)
Mutual labels:  neuroevolution
pacman-ai
A.I. plays the original 1980 Pacman using Neuroevolution of Augmenting Topologies and Deep Q Learning
Stars: ✭ 26 (-99.33%)
Mutual labels:  neuroevolution
NEATEST
NEATEST: Evolving Neural Networks Through Augmenting Topologies with Evolution Strategy Training
Stars: ✭ 13 (-99.67%)
Mutual labels:  neuroevolution
denser-models
cdv.dei.uc.pt/denser/
Stars: ✭ 49 (-98.74%)
Mutual labels:  neuroevolution
NeuralFish
Neuroevolution in F#
Stars: ✭ 28 (-99.28%)
Mutual labels:  neuroevolution
ScaryFlight
Just another yet FlappyBird-style game.
Stars: ✭ 24 (-99.38%)
Mutual labels:  flappybird
AsciiBird
ASCII version of the addictive Flappy Bird game.
Stars: ✭ 34 (-99.13%)
Mutual labels:  flappybird
DeepHyperNEAT
A public python implementation of the DeepHyperNEAT system for evolving neural networks. Developed by Felix Sosa and Kenneth Stanley. See paper here: https://eplex.cs.ucf.edu/papers/sosa_ugrad_report18.pdf
Stars: ✭ 42 (-98.92%)
Mutual labels:  neuroevolution
Tensorflow-Neuroevolution
Neuroevolution Framework for Tensorflow 2.x focusing on modularity and high-performance. Preimplements NEAT, DeepNEAT, CoDeepNEAT, etc.
Stars: ✭ 109 (-97.2%)
Mutual labels:  neuroevolution
flappy-bird
🐦 A clone of a famous game, the Flappy Bird, made in Javascript and HTML Canvas API.
Stars: ✭ 37 (-99.05%)
Mutual labels:  flappybird
flappybird
A 1:1 Flappy Bird Clone written 100% in swift!
Stars: ✭ 186 (-95.22%)
Mutual labels:  flappybird
evo-NEAT
A java implementation of NEAT(NeuroEvolution of Augmenting Topologies ) from scratch for the generation of evolving artificial neural networks. Only for educational purposes.
Stars: ✭ 34 (-99.13%)
Mutual labels:  neuroevolution
Neatron
Yet another NEAT implementation
Stars: ✭ 14 (-99.64%)
Mutual labels:  neuroevolution
Sharpneat
SharpNEAT - Evolution of Neural Networks. A C# .NET Framework.
Stars: ✭ 273 (-92.98%)
Mutual labels:  neuroevolution
Cerebrum
Cerebrum.js is a neural network library created in pure JavaScript.
Stars: ✭ 25 (-99.36%)
Mutual labels:  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.

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].