Computer system designs Mario levels after watching them on Twitch or YouTube

Researchers at Georgia Tech have created a computer system that sees Super Mario Bros. gameplay videos in YouTube or Twitch and creates its own “original new sections” of the classic title.

By analyzing gameplay as well as elements (such as blocks, pipes or coins) in the levels from the classic and renowned platform video game Super Mario Bros., the computer system re-positions the elements into the game. It also analyzes player behavior.

“An initial evaluation of our approach indicates an ability to produce level sections that are both playable and close to the original without hand coding any design criteria,” said Matthew Guzdial, lead researcher and Ph.D. student in Computer Science at Georgia Tech.

“Our system creates a model or template, and it’s able to produce level sections that have never been seen before, do not appear random and can be traversed by the player,” says Mark Riedl, associate professor of Interactive Computing.

The research is titled “Toward Game Level Generation from Gameplay Videos.”

[Source]: Georgia Tech: Georgia Tech Researchers Train Computer to Create Games by Watching YouTube.