Facebook researchers have chosen Minecraft as the training ground for the development of the next stage of artificial intelligence, as the technology looks to conquer a major challenge.
A.I. systems have been learning to carry out specific tasks, including playing soccer and filling in gaps in images, and have proven to be better at some of them than humans, such as in games such as in Texas Hold ’em poker and Quake III‘s Capture the Flag mode.
One of the biggest limitations of the current forms of A.I. is that, while they may excel at a specific activity, they are unable to deal with multiple tasks. Facebook Research’s Arthur Szlam and his colleagues, who have started working on an A.I. assistant that can perform a variety of tasks, have decided to break through the limitation with the help of Minecraft.
Minecraft, possibly the best-selling video game of all time, allows players to move around a 3D environment, exploring and building in a limitless world. The game’s infinite variety, in combination with simple and predictable rules, makes it an ideal environment for training A.I.
The goal of Szlam and his team is to create an A.I. assistant that is capable of helping people with different kinds of tasks, and they believe that Minecraft will help them achieve that. A generalist A.I. assistant will be more useful to the regular user, compared to an A.I. system that can only do one thing well.
“Instead of superhuman performance on a single difficult task, we are interested in competency across a large number of simpler tasks, specified (perhaps poorly) by humans,” Szlam and his team wrote in their research.
Within Minecraft, the A.I. assistant will need to learn the various concepts of the game and the nature of the possible requests. The requests may become very complex, but the opportunity for learning is massive, with the possibility of pushing A.I. research to the next level.
Szlam and his team have uploaded data and code for a baseline Minecraft assistant that is available to try. Perhaps this is a very early look at the generalist A.I. that will be the future of the technology.
- Neuro-symbolic A.I. is the future of artificial intelligence. Here’s how it works
- Revisiting the rise of A.I.: How far has artificial intelligence come since 2010?
- Mind-reading A.I. analyzes your brain waves to guess what video you’re watching
- Facebook is using Minecraft to train AI assistants, one block at a time
- A.I. headphones could warn distracted pedestrians when there’s traffic around