Researchers introduced AlphaZero, a computer program capable not only of mastering superlatives in some of the most complicated board games such as chess, shogi and Go, but also learning to play them without prior notice. , except for the rules of each game. "
The system was created by experts from the British company DeepMind, which is owned by Alphabet, the parent company of Google.
The results that the researchers said represent an important step in the development of an AI player who can quickly learn and manage any game.
Chess, Shogi and Go
Since the 1997 Deep Blue chess program defeated Gary Kasparov in 1997, AI games have become more advanced and can defeat people in increasingly complex games.
Even in other abstract strategy games such as shogi and go, both significantly more complex than chess, they were also dominated by machines.
The novelty of AlphaZero, developed by David Silve and his collaborators at DeepMind, is that he avoids the need for information derived from people and instead he can learn chess, shogi and go repeatedly against one another, one of the games
The system succeeded in defeating the most advanced AI programs, which did not specialize in these three games after several hours of self-study.
As a result, researchers now have to turn to a new generation of games, such as multiplayer video games, to address other challenges for AI systems.
<! – Download the attached document of this report ->