custom ad
NewsFebruary 26, 2015

Software learns to play Atari games from the 1980s, but it isn't so great at Ms. Pac-Man WASHINGTON -- Computers already have bested human champions in "Jeopardy!" and chess, but artificial intelligence now has gone to master an entirely new level: "Space Invaders."...

By SETH BORENSTEIN ~ Associated Press
A youth tries a Ms. Pac-Man TV game Oct. 5, 2004, in New York. Google scientists have cooked up software that can do better than humans on dozens of Atari video games from the 1980s. But the computer hasn't mastered Ms. Pac-Man. (Associated Press)
A youth tries a Ms. Pac-Man TV game Oct. 5, 2004, in New York. Google scientists have cooked up software that can do better than humans on dozens of Atari video games from the 1980s. But the computer hasn't mastered Ms. Pac-Man. (Associated Press)

Software learns to play Atari games from the 1980s, but it isn't so great at Ms. Pac-Man

WASHINGTON -- Computers already have bested human champions in "Jeopardy!" and chess, but artificial intelligence now has gone to master an entirely new level: "Space Invaders."

Google scientists have cooked up software that can do better than humans on dozens of Atari video games from the 1980s, like video pinball, boxing, and "Breakout." But computers don't seem to have a ghost of a chance at "Ms. Pac-Man."

The aim is not to make video games a spectator sport, turning couch potatoes who play games into couch potatoes who watch computers play games. The real accomplishment: computers that can teach themselves to succeed at tasks, learning from scratch, trial and error, just like humans.

Receive Daily Headlines FREESign up today!

The computer program, called Deep Q-network, wasn't given much in the way of instructions to start, but in time, it did better than humans in 29 of 49 games, according to a new study released Wednesday by the journal "Nature." It's a first time an artificial intelligence program bridged different types of learning systems, said study author Demis Hassabis of Google DeepMind in London.

Deep Q "can learn and adapt to unexpected things," Hassabis said in a news conference. "These types of systems are more human-like in the way they learn."

Nothing about Deep Q is customized to Atari or to a specific game. The idea is to create a "general learning system" that can figure tasks out by trial and error and eventually to stuff even humans have difficulty with, Hassabis said. This program, he said, "is the first rung of the ladder."

But to some ways of thinking, Deep Q wasn't even as smart as a toddler, because it can't transfer learned experiences from one situation to another, and it doesn't get abstract concepts, Hassabis said.

Deep Q had trouble with "Ms. Pac Man" and "Montezuma's Revenge" because they are games that involve more planning ahead, he said.

Story Tags
Advertisement

Connect with the Southeast Missourian Newsroom:

For corrections to this story or other insights for the editor, click here. To submit a letter to the editor, click here. To learn about the Southeast Missourian’s AI Policy, click here.

Advertisement
Receive Daily Headlines FREESign up today!