Sunday, 17 December 2017
Latest news
Main » Google's DeepMind AI masters chess, beating expert software

Google's DeepMind AI masters chess, beating expert software

07 December 2017

Google's AI, AlphaZero, developed a "superhuman performance" in chess in just four hours. Though many hurdles remain, Google's paper clearly indicates AlphaZero is a massive step in the right direction.

"From a scientific point of view, it's the latest in a series of dazzling results that DeepMind has produced", Michael Wooldridge, Professor at the University of Oxford told the BBC.

In their new paper, the team outlines how the very latest AlphaZero AI takes the self-playing reliance - called reinforcement learning - and applies it with a much more generalised streak that gives it a broader focus to problem solving.

Mass. Hit With Early Flu Season
This year, there are concerns that the shot is not very effective, but experts are still encouraging people to get it. To find a location near you to get the flu vaccine, go to healthvermont.gov/flu or dial 2-1-1.

Google hasn't commented on AlphaZero's achievement as the study hasn't yet been peer-reviewed.

From virtual reality to providing internet access to remote parts of the globe, search-engine giant Google has funneled significant funding into a variety of projects. The Go victory was, so far, considered the bleeding edge of its ability, but DeepMind has kept working on and refining this AI, culminating in a startling success in October: a new, fully autonomous version of the AI, which only learned by playing against itself, never humans, bested all its previous incarnations. Playing 100 matches against the former world champion chess program, Stockfish 8, Google's program came out on top. Starting without any strategy to use as a crutch, the AI needed only four hours to master the game to such extent that it destroyed Stockfish - the highest-rated chess-playing program today. Moreover, it taught itself how to play few games including Space Invaders and Pong. AlphaZero won 25 games in which it played with white (gaining the first-move advantage) and a further three in which it played black. The last 72 games were a draw with AlphaZero recording no losses and Stockfish recording no wins. 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.

There is a storied history of artificial intelligence programs taking on the greatest human game players.

Google's DeepMind AI masters chess, beating expert software