https://github.com/ikergarcia1996/neuroevolution-flappy-bird

A comparison between humans, neuroevolution and multilayer perceptrons playing Flapy Bird implemented in Python
https://github.com/ikergarcia1996/neuroevolution-flappy-bird

ai ai-tutorial artificial-evolution artificial-intelligence artificial-neural-networks deep-learning flappy-bird game-programming genetic-algorithm jupyter-notebook machine-intelligence machine-learning machine-learning-algorithms multilayer-perceptron-network neat neat-python neural-network neural-networks neuroevolution python

Last synced: 10 days ago
JSON representation

A comparison between humans, neuroevolution and multilayer perceptrons playing Flapy Bird implemented in Python

• Host: GitHub
• URL: https://github.com/ikergarcia1996/neuroevolution-flappy-bird
• Owner: ikergarcia1996
• License: mit
• Created: 2017-12-26T10:14:34.000Z (about 7 years ago)
• Default Branch: master
• Last Pushed: 2017-12-28T03:14:26.000Z (about 7 years ago)
• Last Synced: 2024-12-29T13:44:40.875Z (23 days ago)
• Topics: ai, ai-tutorial, artificial-evolution, artificial-intelligence, artificial-neural-networks, deep-learning, flappy-bird, game-programming, genetic-algorithm, jupyter-notebook, machine-intelligence, machine-learning, machine-learning-algorithms, multilayer-perceptron-network, neat, neat-python, neural-network, neural-networks, neuroevolution, python
• Language: Jupyter Notebook
• Homepage:
• Size: 18.1 MB
• Stars: 21
• Watchers: 3
• Forks: 8
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# Flappy Bird: Human vs NEAT vs MLP

The goal of the project is to apply NEAT to evolve the network architecture of Deep Neural Networks for improving their performance on a given classification task, in this case the game Flappy Bird, the goal is to determine if for a given input the bird must jump or no to avoid hitting the pipes.

This repository contains a Jupyter Notebook where is possible to compare a Human, a Neat implementation and a multilayer perceptron playing Flappy Bird. 



 



## Input

For both, neuroevolution algorithm and multilayer perceptron the input is the same:

 

    1) Distance in the X axis from the bird to the next pipe.

    2) Distance in the Y axis form the bird to the lowest point of the pipe in the top.

    3) Distance in the Y axis from the bird to the highest point of the pipe in the top

    4) Distance in the Y axis from the bird to the top of the map.

    5) Distance in the Y axis from the bird to the bottom of the map.

    







## Results

In this project we probe that NEAT can improve the performance of a DNN. We found that NEAT can be useful to reduce the complexity of our models. NEAT is able to produce networks that produce similar results to the MLP but much less complex. We have been able to use NEAT to reduce the complexity of our model. We went from 20 neurons and 98 weights in the MLP to 7-8 neurons and 6-10 weights, with is a huge complexity reduction.

More information available in the [documentation](https://github.com/ikergarcia1996/Flappy-Bird-NEAT-vs-DEEP/releases/).

![INPUT](https://github.com/ikergarcia1996/Flappy-Bird-NEAT-vs-DEEP/blob/master/DemoImages/comp.png?raw=true)

## Authors

```

Iker García Ferrero - ikergarcia1996

Gonzalo Pierola - Guamedo

```

## How to run

To run this project you need [Python](https://www.python.org/) and [Jupyter Notebook](http://jupyter.org/).

Also you will need to install all the python libraries specified in the "README.md" inside the "Jupyter Notebook" folder.

## Documentation

Documentation is available in the [releases section](https://github.com/ikergarcia1996/Flappy-Bird-NEAT-vs-DEEP/releases/) with the corresponding release.

## Flappy Bird Game

The implementation of the Flappy Bird Game that we used for this project is based on this code:

[Gamedevlapse: Create Flappy Bird in Python \[Time Lapse\] (youtube)](https://youtu.be/h2Uhla6nLDU)