Ryan Swanstrom

Machine Learning to Play Super Mario

A fun video to watch. Very Impressive!

The technique uses a genetic algorithm to training a neural network. A paper with more details can be found at, Evolving Neural Networks through Augmenting Topologies (NEAT)

Posted

in

,

by

Ryan Swanstrom

Tags:

, , ,

Comments

One response to “Machine Learning to Play Super Mario”

  1. TGIF: MarI/O – Machine Learning for video games | yokekeong

    […] Watch this interesting machine learning task where a machine learns how to play Super Mario. [Via Data Science 101] […]

    Reply

Leave a Reply