Microsoft is attempting to create a more intelligent and intuitive type of artificial intelligence by training computers to play Minecraft efficiently on their own, it announced in an official blog post.
“In the airy, loft-like Microsoft Research lab in New York City, five computer scientists are spending their days trying to get a Minecraft character to climb a hill,” the team writes. That may seem like a pretty simple job for some of the brightest minds in the field, until you consider this: “The team is trying to train an artificial intelligence agent to learn how to do things like climb to the highest point in the virtual world, using the same types of resources a human has when she learns a new task” states the post.
“That means that the agent starts out knowing nothing at all about its environment or even what it is supposed to accomplish. It needs to understand its surroundings and figure out what’s important – going uphill – and what isn’t, such as whether it’s light or dark,” it explaines. “It needs to endure a lot of trial and error, including regularly falling into rivers and lava pits. And it needs to understand – via incremental rewards – when it has achieved all or part of its goal.”
The research is reportedly made possible through a platform developed in the UK called AIX, which allows programmers to conduct artificial intelligence experiments within the popular gaming world of Minecraft.
“Minecraft is the perfect platform for this kind of research because it’s this very open world,” said AIX platform developer Katja Hofmann. “You can do survival mode, you can do ‘build battles’ with your friends, you can do courses, you can implement our own games. This is really exciting for artificial intelligence because it allows us to create games that stretch beyond current abilities”.
Though AIX is currently only available to a handful of researchers at Microsoft, the software will be released in an open-source format this summer for Windows, Mac OS, and Linux.
Charlie Nash is a frequent contributor to Breitbart Tech and former editor of the Squid Magazine. You can follow him on Twitter @MrNashington.