Skip to content

Latest commit

 

History

17 Commits

Folders and files

NameName
Last commit message
Last commit date
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Solving Snake using Genetic Algorithm and Neural Networks

This is an implementation of genetic algorithms combined with neural networks also known as neuroevolution

snake

The algorithm doesnt perform amazing and i think thats due to the fact that i always spawn snakes on random environments so they are never memorizing. Further proof of this is there are snakes in training phase that get to the 20 food levels but i think randomness of the environment is more realistic.

TO-DO

-Tune hyperparameters to get the best result

-Document the remaining files

-Fix roulette wheel selection function

-Fix crossover_midpoint

-Clean up game.py

About

Training neural networks using genetic algorithms

Resources

Stars

0 stars

Watchers

1 watching

Forks

Releases

Packages

Contributors

Languages