MarI/O – Machine Learning for Video Games – Artificial Intelligence Uses Neural Networks to Master Super Mario
[mbYTPlayer url=”https://www.youtube.com/watch?v=qv6UVOQ0F44″ opacity=”.5″ quality=”medium” ratio=”auto” isinline=”false” showcontrols=”false” realfullscreen=”true” printurl=”true” autoplay=”true” mute=”true” loop=”true” addraster=”true” stopmovieonblur=”false” gaTrack=”false”]
We have seen the future, and artificial intelligence takes over. MarI/O, created by gamer Seth Bling, is just the tip of the iceberg. This AI had no idea how to play the game at first, but after some simple parameters were set in the form of “fitness” levels, it was incentivized to continue trying new ideas. You read that right, each level used new ideas, and it remembers what worked, while discarding its mistakes. After 34 steps, using NeuroEvolution of Augmenting Topologies, MarI/O figured out that jumping was the key to complete the stage. What’s crazy is that the AI is so good now that any further attempts on the stage will all result in successful completion.