Automated Super Mario World gameplay through machine learning

Seth Bling made a bot — MarI/O — that automatically learns how to play Super Mario World. It’s based on research by Kenneth O. Stanley and Risto Miikkulainen from 2002 that uses neural networks that evolve with a genetic algorithm. MarI/O starts out really dumb, just standing in place, but after enough simulations it get smart enough to navigate the world.

Code available here and the paper from Stanley and Mikkulainen is here.

See also: the genetic algorithm walkers.

Favorites

One Dataset, Visualized 25 Ways

“Let the data speak” they say. But what happens when the data rambles on and on?

Top Brewery Road Trip, Routed Algorithmically

There are a lot of great craft breweries in the United States, but there is only so much time. This is the computed best way to get to the top rated breweries and how to maximize the beer tasting experience. Every journey begins with a single sip.

How to Spot Visualization Lies

Many charts don’t tell the truth. This is a simple guide to spotting them.

The Most Unisex Names in US History

Moving on from the most trendy names in US history, let’s look at the most unisex ones. Some names have …