AlphaGo is the first computer program to defeat a professional human Go player, the first to defeat a Go world champion, và is arguably the strongest Go player in history.
Bạn đang xem: Lee sedol là ai
Go is known as the most challenging classical game for artificial intelligence because of its complexity.
Despite decades of work, the strongest Go computer programs could only play at the cấp độ of human amateurs. Standard AI methods, which test all possible moves và positions using a tìm kiếm tree, can’t handle the sheer number of possible Go moves or evaluate the strength of each possible board position.
Go originated in Trung Quốc over 3,000 years ago. Winning this board game requires multiple layers of strategic thinking.
Two players, using either White or blaông xã stones, take turns placing their stones on a board. The goal is lớn surround và capture their opponent"s stones or strategically create spaces of territory. Once all possible moves have sầu been played, both the stones on the board và the empty points are tallied. The highest number wins.
As simple as the rules may seem, Go is profoundly complex. There are an astonishing 10 to lớn the power of 170 possible board configurations - more than the number of atoms in the known universe. This makes the game of Go a googol times more complex than chess.
To capture the intuitive sầu aspect of the game, we needed a new approach.
We created AlphaGo, a computer program that combines advanced tìm kiếm tree with deep neural networks. These neural networks take a mô tả tìm kiếm of the Go board as an đầu vào and process it through a number of different network layers containing millions of neuron-lượt thích connections.
One neural network, the “policy network”, selects the next move to play. The other neural network, the “value network”, predicts the winner of the game.We introduced AlphaGo khổng lồ numerous amateur games lớn help it develop an understanding of reasonable human play. Then we had it play against different versions of itself thousands of times, each time learning from its mistakes.
Over time, AlphaGo improved và became increasingly stronger & better at learning và decision-making. This process is known as reinforcement learning. AlphaGo went on khổng lồ defeat Go world champions in different global arenas và arguably became the greatest Go player of all time.