Google DeepMind Masters Chess

Ceria Alfonso
Diciembre 7, 2017

Google has not commented about the research until it is published. Because of this, it is easy to forget the company's somewhat less publicized endeavors into artificial intelligence. DeepMind's AlphaZero program, which teaches itself from scratch, achieved "superhuman" knowledge of chess in less than the amount of time you'd spend, say, watching the extended version of The Lord of the Rings: Return of the King. The AI system's latest success is within this vein, but in reality is about so much more than that. At least, that's the case with Google's newest AI installment AlphaZero.

"The games AlphaZero played show it can calculate some incredibly creative positional bombs, the depth of which are far beyond anything humans or chess computers have come up with", said David Kramaley, who runs chess education site Chessable, according to The Telegraph. In a closed-door event, AlphaZero defeated Stockfish in 28 out of 100 games, tying the other 72 matches, ending the bout with zero losses.

Google's DeepMind lab has been working on this technology for years, beginning with AlphaGo, which learned how to play the Chinese board game, Go and became the first AI to beat a Go grandmaster.

The current AlphaZero takes the reinforcement learning of AlphaGo Zero and uses it in a broader approach. The AI system, after managing to master Go in just eight hours, unbelievably accomplished the same for chess with just four hours of practice.

More news: Virus AH3N2, el más contagioso y agresivo esta temporada

Google's DeepMind division said that its AlphaZero artificial intelligence (AI) program played 100 games against the world's leading software Stockfish 8, and had either won them or concluded in a draw. In 1997, the IBM supercomputer Deep Blue beat world champion chess player Garry Kasparov by computing and evaluating positions that were programmed into the machine with the help of chess masters, but AlphaZero is different because it had to teach itself the positions to begin with.

Based on this, it would seem that AlphaZero demonstrates the sort of "generic" thinking ability that Google is attempting to cultivate in their AI systems.

DeepMind's founders hope AlphaZero can be used to solve pressing societal issues.

Otros informes por

Discuta este artículo

SIGUE NUESTRO PERIÓDICO