Skip to content

Marionette (Mario-net) is a system for training neural networks to play classic NES games.

Notifications You must be signed in to change notification settings

magneticflux-/Marionette

Repository files navigation

Marionette

Marionette is designed to train neural networks to play NES game, in a fashion akin to a marionette. The name is also a play on the words "Mario" and "Net", referencing the first supported NES game. Eventually, I hope to train neural networks on the raw visual data, instead of the contents of the NES's RAM.

Marionette uses the NEAT algorithm detailed in Kenneth Stanley's paper, "Evolving Neural Networks through Augmenting Topologies".

Supported Games:

  • Super Mario Bros. (1987)

Important!

This project must be built with Java-NEAT, JNSGA-II, and halfnes-headless. I organize it by making a Gradle super-project to build all modules together.

About

Marionette (Mario-net) is a system for training neural networks to play classic NES games.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages