Elementary

Twitter Facebook Pinterest icon Pinterest
Humans Teamed up With a New Kind of AI to Crush a Notoriously Difficult Video Game
Humans Teamed up With a New Kind of AI to Crush a Notoriously Difficult Video Game

A team of scientists at Uber’s artificial intelligence lab just pulled off one of the major outstanding challenges in AI research — something so advanced and difficult that some wondered whether an AI system would ever figure it out.

This article was originally published on Futurism. This is just a theme demo site.

That’s right. The team, the MIT Technology Review reports, built an algorithm that’s really, really good at old-school video games “Pitfall!” and “Montezuma’s Revenge.”

And while it did take some help from humans, according to Uber’s blog post on the soon-to-be-published research, the algorithm learned to rack up scores no human player could ever reach.

Team work is important

When AI learns how to play and subsequently master a video game, it’s often by way of reinforcement learning, a type of algorithm that learns to seek out things that it has been programmed to treat as a reward. An ever-rising video game score makes for eager reinforcement learning-driven AI gamers, but games like “Pitfall!” and “Montezuma’s Revenge” don’t immediately (or often) increase the player’s score, MIT Tech Reviewmentions.

Hi. I've been on the road for 6 years, visited 70-something countries and documented everything here on my blog along the way. Thanks for stopping by!
More posts by Jane Doe.
New AI Is Peering Into the Nuclear Cores of Distant Stars
New Robot Is “On The Path to Machine Self-Awareness,” Says Creator

Subscribe to Elementary