Skip to content

eyny/deep-learning-gaming

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

7 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

deep-learning-gaming

This was the graduation project that I prepared to earn my Computer Engineering Bachelor's Degree. It learns how to play Super Mario Bros. game using deep reinforcement learning which can be considered a subset of machine learning. It uses Keras for its deep learning library with TensorFlow backend. Gym Super Mario environment bundle is used for OpenAI Gym. At the first stage, the best model from three different models for this problem is founded. During the second stage, the model is trained on the first level of Super Mario Bros for a long duration. At the last stage, the trained model is used on a different level. It is investigated if there is a significant improvement compared to a random model.

Requirements

  • Keras 2.1.5
  • FCEUX 2.2.2
  • Gym Super Mario 0.0.7
  • OpenAI Gym 0.92

About

A deep learning project to play Super Mario Bros. using Keras

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages