American Go E-Journal

Google’s AlphaZero destroys highest-rated chess engine in 100-game match

Thursday December 7, 2017

Chess changed forever today. And maybe the rest of the world did, too.2017.12.07_alphazero-stockfish

A little more than a year after AlphaGo sensationally won against the top Go player, the artificial-intelligence program AlphaZero has obliterated the highest-rated chess engine.

Stockfish, which for most top players is their go-to preparation tool, and which won the 2016 TCEC Championship and the 2017 Chess.com Computer Chess Championship, didn’t stand a chance. AlphaZero won the closed-door, 100-game match with 28 wins, 72 draws, and zero losses.

Oh, and it took AlphaZero only four hours to “learn” chess. Sorry humans, you had a good run.

That’s right — the programmers of AlphaZero, housed within the DeepMind division of Google, had it use a type of “machine learning,” specifically reinforcement learning. Put more plainly, AlphaZero was not “taught” the game in the traditional sense. That means no opening book, no endgame tables, and apparently no complicated algorithms dissecting minute differences 2017.12.07_michael-adams-demis-hassabisbetween center pawns and side pawns.

This would be akin to a robot being given access to thousands of metal bits and parts, but no knowledge of a combustion engine, then it experiments numerous times with every combination possible until it builds a Ferrari. That’s all in less time that it takes to watch the “Lord of the Rings” trilogy. The program had four hours to play itself many, many times, thereby becoming its own teacher.

“It’s a remarkable achievement, even if we should have expected it after AlphaGo,” GM Garry Kasparov told Chess.com. “It approaches the ‘Type B,’ human-like approach to machine chess dreamt of by Claude Shannon and Alan Turing instead of brute force.”

You can read the full paper here. GM Peter Heine Nielsen said that “After reading the paper but especially seeing the games I thought, well, I always wondered how it would be if a superior species landed on earth and showed us how they play chess. I feel now I know.”

After the Stockfish match, AlphaZero then “trained” for only two hours and then beat the best Shogi-playing computer program “Elmo.”

“[This is] actual artificial intelligence,” said Nielsen. “It goes from having something that’s relevant to chess to something that’s gonna win Nobel Prizes or even bigger than Nobel Prizes. I think it’s basically cool for us that they also decided to do four hours on chess because we get a lot of knowledge. We feel it’s a great day for chess but of course it goes so much further.”

Excerpted from Mike Klein’s December 6 report on chess.com. photo: Deepmind’s Demis Hassabis (right) playing with Michael Adams at the ProBiz event at Google Headquarters London just a few days ago. | Photo: Maria Emelianova/Chess.com.

Share