Skip to content

piochelepiotr/jump

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

17 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

jump

Presentation

This project is an implemeation of a neural network, that learns with a genetic algorithm. The neural network and the genetic algorithm are both coded from scratch, without using an external library, so this project was more about understanding how a genetic algorithm works.

The goal is to make a monster move on a map with a neural network, we learns what are the good moves.

At the end, it works, but for this problem, a neural net isn't effective. The problem is too simple so all the program does is to learn by heart the moves he has to do depending on the environment.

Library

As it was a school project, we had to make our project reusable buy the teacher for future improvments ,so we had to use Evolife. It makes the code more complex to understand.

About

Implementation of a neural network

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published