Historical Milestone: Self-Learning Machine Outplays Brute Force with Surprising Beauty
6 December 2017
Stunning news in the computer world. Brand new DeepMind’s AlphaZero chess engine crushed the best program Stockfish in a 100-game match without losing any single game.
It’s not an ordinary victory. What’s shocking, AlphaZero learned the game from scratch in just 4 hours playing only with itself. Without any human supervision.
Unlike Stockfish, a hand-crafted brute-force algorithm browsing through 70 million positions per second to find its best move, AlphaZero uses it’s neural network and looks up “only” 80 thousand of them. It means this neural brain has much better understanding of each position on the board and so it doesn’t need to check so many combinations.
This human-like understanding of the game is even more astonishing if you look at the games it played. AlphaZero displays remarkable, beauty of the style of play.
Many chess masters became now obsessed with games of AlphaZero, not because of its strength but its human, romantic style of play.
Is Machine Learning The Next Big Thing?
Machine learning is hardly new. But the breakthrough is here. AlphaZero creators proved self-thought computers can be easily much better than hand-crafted human-designed ones. So far it's wasn't so obvious. At least not to general public.
If a computer can learn a game and surpass the 1400-years old human knowledge in just 4 hours, soon enough we may found ourselves in a new era, where computers are designing things better, faster, and even beautiful.