Google’s AI Mastered All The Chess Knowledge In History
Chess isn’t an easy game by human standards. But for an artificial intelligence powered by a formidable, almost alien mindset, this game can be mastered in a few spare hours.
In a new paper, Google researchers detail how their latest AI evolution, AlphaZero, developed “superhuman performance“ in chess, taking just 4 hours to learn the rules before obliterating the world champion chess program, Stockfish.
After being programmed with only the known rules for chess (no strategies) in just 4 hours AlphaZero had mastered the game to to the extent it was able to best the highest-rated chess-playing program Stockfish.
In a series of 100 games against Stockfish, AlphaZero won 25 games while playing as white, and 3 of them as black. The rest of the contest were draws and Zlphazero counted no loses and Stockfish no wins.
“We now know who our new overlord is,” said chess researcher David Kramaley, the CEO of chess science website Chessable. “It will no doubt revolutionise the game, but think about how this could be applied outside chess. This algorithm could run cities, continents, universes.”
Developed by Google’s DeepMind AI lab, AlphaZero is more generic version of AlphaGo Zero, which specialises in playing the Chinese board game, Go.
DeepMind has been refining this AI for years, in the process besting a series of human champions who fell like dominoes before the indomitable, “Godlike” neural network. That victory streak culminated in a startling success in October, in which a new fully autonomous version of the AI – which only learns by playing itself, never facing humans – bested all its former incarnations. By contrast, AlphaGo Zero’s predecessors partly learned how to play the game by watching moves made by human players. AlphaGo Zero’s fully self-reliant learning proved devastatingly more effective in one-on-one competition.
“It’s like an alien civilisation inventing its own mathematics,” computer scientist Nick Hynes from MIT told Gizmodo in October. “What we’re seeing here is a model free from human bias and presuppositions. It can learn whatever it determines is optimal, which may indeed be more nuanced that our own conceptions of the same.”
AlphaZero doesn’t just play chess, it also plays Shogi (Japanese chess) and Go Too – and it also took 2,8 hours to master those games as well.
For now, Google and Deepmind’s computer scientists don’t give official statements and any comments connected with their newest research, which hasn’t been peer-reviewed.
By what we can tell so far, the newest computer games and programs are certainly overwhelming by the fact that they become far more intelligent and beat the artificial intelligence by their previous works, but the process and embittering doesn’t stop here and now.
“I always wondered how it would be if a superior species landed on Earth and showed us how they played chess,” grandmaster Peter Heine Nielsen told the BBC.
“Now I know.”
The findings are available at preprint website arXiv.
Source: Science Alert