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.
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.