OpenAI Artificial Intelligence Hide and Seek
We’re possibly less than a decade away from self-conscious artificial intelligence capable of learning on its own, and this latest project gets us one step closer. Researchers OpenAI took an unusual approach at developing AI, one inspired by natural selection and competition. Put simply, they pit multiple AI agents against each other to compete for conflicting goals and found that it developed new sophisticated behavior in the long term. Read more for a video and additional information.

These AI agents are split between “hiders” / “seekers,” and their roles are exactly as they sound. The hiders get a set time to hide, while the seekers are frozen, with each of the AI agents left on their own to discover ways to make use of their environment to achieve their goals. It uses reinforcement learning, the same technique used to create bots that can play complicated online massively multiplayer games such as StarCraft and Dota 2.