Alphabet’s DeepMind Technologies created a neural network that learns how to play video games in a fashion similar to that of humans. It’s also a Neural Turing machine, or a neural network capable of accessing an external memory like a conventional Turing machine, resulting in a computer that mimics the short-term memory of the human brain. Read more for a video show just some of the games it has mastered, including several Atari classics, like Breakout.
Unlike other AIs, DeepMind’s system is not pre-programmed, as it learns from experience, using only raw pixels as data input. This system is tested on video games, notably early arcade games, such as Space Invaders or Breakout. Without altering the code, the artificial intelligence begins to understand how to play the game, and after a while, it plays more efficiently than any human ever could.
DeepMind has so far proved that an AI system could surpass human abilities in games such as Pong, Breakout, Space Invaders, Seaquest, Beamrider, Enduro and Q*bert. It has been applied to video games made in the 1970s and 1980s, while work is still ongoing for more complex 3D games such as Doom, which first appeared in the early 1990s.