Programmers at OpenAI, an artificial intelligence research company, recently taught a gaggle of intelligent artificial agents — bots — to play hide-and-seek. Not because they cared who won: The goal was to observe how competition between hiders and seekers would drive the bots to find and use digital tools. The idea is familiar to anyone who’s ever played the game in real life; it’s a kind of scaled-down arms race. When your opponent adopts a strategy that works, you have to abandon what you were doing before and find a new, better plan. It’s the rule that governs games from chess to StarCraft II; it’s also an adaptation that seems likely to confer an evolutionary advantage.
So it went with hide-and-seek. Even though the AI agents hadn’t received explicit instructions about how to play, they soon learned to run away and chase. After hundreds of millions of games, they learned to manipulate their environment to give themselves an advantage. The hiders, for example, learned to build miniature forts and barricade themselves inside; the seekers, in response, learned how to use ramps to scale the walls and find the hiders.
These actions showed how AI agents could learn to use things around them as tools, according to the OpenAI team. That’s important not because AI needs to be better at hiding and seeking, but because it suggests a way to build AI that can solve open-ended, real-world problems.
We were not expecting [box surfing] to happen, but it was exciting when it did.
Bowen Baker, OpenAI
“This was an impressive use of a tool, and tool usage is incredible for AI systems,” said Danny Lange, a computer scientist and vice president of AI at the video game company Unity Technologies who wasn’t involved with the hide-and-seek project. “These systems figured out so quickly how to use tools. Imagine when they can use many tools, or create tools. Would they invent a ladder?”