Skip to content

An evolutionary neural network trained to play a clone of Super Mario Bros. Created using Tensorflow and LibGDX.

Notifications You must be signed in to change notification settings

artur-sak13/MarioFlowGDX

Repository files navigation

MarioFlowGDX

An evolutionary neural network trained to play a clone of the original NES Super Mario Bros.

This project contains the source code for an evolutionary algorithm optimized artificial neural network trained to play a clone of the first level of Super Mario Bros.

All code was written in Java using the libGDX game development framework and TensorFlow machine intelligence library.

Screenshots

Development Setup

  1. Install Java JDK
  2. Install Gradle
  3. Clone this repository
git clone https://github.com/artur-sak13/MarioFlowGDX.git
  1. Open the project in a Java supporting IDE (i.e. Eclipse, IntelliJ, Netbeans, etc.)
  2. Import the Gradle project settings
  3. Edit your run configuration and make sure that core/assets is set as your working directory
  4. Run the project and have fun!

Usage

You can either run com.artursak.mariobros.desktop as a Java application to build the project or run the .jar file

java -jar MarioBros.jar

Controls

  • Left arrow or A -> Move Left
  • Right arrow or D -> Move Right
  • Up arrow or W -> Jump
  • Spacebar -> Fireball

Note: Fire Mario and stars items are not yet implemented so Mario can throw fireballs from the start.

Other

Check out all of my projects!

https://github.com/artur-sak13/

About

An evolutionary neural network trained to play a clone of Super Mario Bros. Created using Tensorflow and LibGDX.

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages