Facebook is building an AI minicraft game

Minecraft is one of the best-selling video games of all time, beating classics like Tetris and Super Mario Bros., with more than 170 million copies sold. More than 90 million people play the game every single month.

It turns out that video games may be an excellent method of teaching skills to artificial intelligence assistants. That’s the theory of a group of researchers working for Facebook, who have focused on Minecraft as a potential teaching tool for building generalist AI — a so-called ‘virtual assistant.’ The research team isn’t trying to build an artificial intelligence that’s super-good at classifying images or other content — it wants to build a generalist AI that can perform a much larger number of tasks reasonably well.

Researchers at Google have already trained AI systems to compete with professionals in games such as Go and Starcraft II. But Facebook researchers think this AI system could tackle a new problem by helping computers parse and understand complex human speech.

The authors of the paper target three specific achievements: Create synergy between machine-learning and non-machine-learning components, allowing them to work together; create a “grounded” natural language simulation that allows the AI to understand what players want it to do, and can communicate its success or failure back to the end-user; and create an AI that shouldn’t just be capable of doing what the player wants it to do, but that also its performance should improve based on observation of the human player. 

We intend that the player will be able to specify tasks through dialogue (rather than by just issuing commands), so that the agent can ask for missing information, or the player can interrupt the agent’s actions to clarify. In addition, we hope dialogue to be useful for providing rich supervision. The player might label attributes about the environment, for example “that house is too big”, relations between objects in the environment (or other concepts the bot understands), for example “the window is in the middle of the wall”, or rules about such relations or attributes. We expect the player to be able to question the agent’s “mental state” to give appropriate feedback, and we expect the bot to ask for confirmation and use active learning strategies.

The machine learning code being used for the Facebook-Minecraft bot is available on GitHub. Better AI tools could be useful in many games, though they could also raise serious questions about what constitutes cheating in multiplayer.