Skip to main content

Facebook taps Minecraft as training ground for next stage of A.I.

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.

Recommended Videos

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.

Aaron Mamiit
Aaron received an NES and a copy of Super Mario Bros. for Christmas when he was four years old, and he has been fascinated…
Google Smart Canvas gets deeper integration between apps
A MacBook with Google Chrome loaded.

Google is updating Smart Canvas, a collaboration experience that debuted last year in the midst of the global pandemic designed for better collaboration and remote work, with new improvements targeting hybrid work.

The Internet search giant claims that the latest enhancements to Smart Canvas help to improve collaboration and speed up your workflow when using Google Workspace apps, such as Google Docs and Sheets.

Read more
Voyage is an A.I. gaming paradise where bots write the rules
An AI draws a cowboy pizza in Pixel This.

If you play a lot of video games, you’re no stranger to competing against a machine. Play a game like Halo Infinite long enough and you’ll probably bump into a few bots that aren’t the smartest Spartans on the battlefield. But what if you could play games with a genius A.I. that actually feels like it's listening and responding to you like a human?

Voyage is a new A.I. gaming platform featuring unique games built around machines. The experimental project is spearheaded by Latitude, the studio behind A.I. Dungeon. In that text-based adventure game, a machine fluidly crafts a story by responding to everything a user types, just like an RPG dungeon master. It was an impressive trick in 2019, but it’s only the beginning of what Voyage has in store for players.

Read more
How Nvidia is using A.I. to help Domino’s deliver pizzas faster
Domino's delivery in line.

Nvidia announced a new tool that can help deliver your pizzas faster -- yes, really -- at its fall GTC 2021 event. It's called ReOpt, and it's a real-time logistics tool that Domino's is already using to optimize delivery routes based on time and cost.

ReOpt is a set of logistics-planning algorithms that can find billions of routes to the same location. It utilizes heuristics powered by GPU computing to route vehicles in the most efficient way possible. It's like Google Maps, just way more complex and designed specifically to meet the needs of last-mile delivery.

Read more