AI Learns to Defy Laws of Physics to Win at Hide-and-Seek

Researchers at the OpenAI artificial intelligence laboratory developed bots that trained themselves to cooperate by playing hide-and-seek. Scientists at the OpenAI artificial intelligence (AI) laboratory have developed AI bots that trained themselves to cooperate by playing hide-and-seek. The team had the bots play the game in a simulated environment containing fixed walls and movable boxes; each bot had its own perspective of its surroundings, and could not directly communicate with other bots. The bots that hid quickly deduced the fastest way to fool seekers was to find objects in the environment with which to conceal themselves; the seekers learned they could manipulate objects like ramps to overcome obstacles like walls. The bots learned that cooperation--like passing objects to each other or co-building a hideout--was the quickest way to win.