Automated Super Mario World gameplay through machine learning

Jun 15, 2015

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

10 Best Data Visualization Projects of 2015

These are my picks for the best of 2015. As usual, they could easily appear in a different order on a different day, and there are projects not on the list that were also excellent.

Visualizing the Uncertainty in Data

Data is an abstraction, and it’s impossible to encapsulate everything it represents in real life. So there is uncertainty. Here are ways to visualize the uncertainty.

19 Maps That Will Blow Your Mind and Change the Way You See the World. Top All-time. You Won’t Believe Your Eyes. Watch.

Many lists of maps promise to change the way you see the world, but this one actually does.

Life expectancy changes

The data goes back to 1960 and up to the most current estimates for 2009. Each line represents a country.