DeepMind's AI is now beating humans at Quake because winning in Go wasn't terrifying enough

Business Insider | 7/4/2018 | Fortune (Posted by) Level 3
Click For Photo:

A DeepMind AI system has learned how to play multiplayer video game Quake at a human level.

The AI didn't know the rules of the game but was able to learn quickly, DeepMind said.

Breakthrough - Years - DeepMind - Program - Champion

The breakthrough comes two years after another DeepMind program defeated the human champion of the game Go.

Two years ago, DeepMind drew headlines by creating an AI system that defeated the world champion of the game Go. Now another program at the Alphabet subsidiary has learned how to play the popular multiplayer video game Quake.

DeepMind - Tuesday - Innovations - Reinforcement - Learning

DeepMind said Tuesday that it had developed innovations and reinforcement learning that enabled an artificial-intelligence system to achieve human-level performance in Quake III Arena's Capture the Flag, a 3-D first-person multiplayer game.

DeepMind said that learning to play Capture the Flag was intended as an exercise in which several individual agents must act independently, while learning to interact incorporate with each other. "This is an immensely difficult problem — because with co-adapting agents the world is constantly changing,"...
(Excerpt) Read more at: Business Insider
Wake Up To Breaking News!
Sign In or Register to comment.

Welcome to Long Room!

Where The World Finds Its News!