Mario AI built with Machine Learning - Difficulty 0

This is a Mario AI which I created for my Game AI class. It uses the competition code from http://julian.togelius.com/mariocompetition2009/. Our assignment required that the agent be built with machine learning; I used a k-Nearest Neighbors algorithm and trained my agent with Robin Baumgarten's agent, who won the 2009 competition. The agent entirely learned all of its behavior; the only logic it uses is to recognize features in the world.

In this video, Mario makes his way through a level with Difficulty 0. In this difficulty, there are few enemies and no pits, and Mario was able to learn how to navigate these environments very well.

Category:

Science & Technology

Tags:

• marioDiff0