Breakthrough computer teaches itself without humans

Photo / Thinkstock

A new kind of artificial intelligence has learned to play vintage video games without any prior instructions in a bid to achieve human-like scoring abilities, scientists claim.

The machine learns by itself from scratch, using a trial and error approach reinforced by the reward of a score in the game.

This is fundamentally different from previous game-playing "intelligent" computers.

The system of software algorithms is called Deep Q-network and has learned to play 49 classic Atari games such as Space Invaders and Breakout, with only the help of information about the pixels on a screen and the scoring method.

Scientists behind the development say the software is a breakthrough in artificial intelligence capable of learning without being fed instructions from human experts - the classic method for chess playing machines like IBM's Deep Blue computer.

"This work is the first time anyone has built a single, general learning system that can learn directly from experience to master a wide range of challenging tasks, in this case a set of Atari games, and to perform at or better than human level," said Demis Hassabis, a former neuroscientist and founder of DeepMind Technologies, which was bought by Google for $821 million in 2014.

The Deep Q-network played the same game hundreds of times to learn the best way to get high scores. In some games it outperformed humans by learning smart tactics.

In more than half the games, the system was able to achieve more than 75 per cent of the human scoring ability just by trial and error, said a study published in the Nature journal.

"The advantage of these kinds of systems is that they can learn and adapt to unexpected things and the programmers and systems designers don't have to know the solution themselves in order for the machine to master that task," Hassabis said.