Googles AI beats 2nd Dan Go-Player

Ich kenne mich im chinesischen Brettspiel Go nicht aus, aber das Spiel ist wohl ein paar Größenordnungen komplexer als Schach und die Anzahl der Figuren-Konstellationen ist anscheinend größer „than the number of atoms in the universe“. Facebook arbeitet schon eine ganze Weile an einer künstlichen Intelligenz, die Go beherrschen soll, The Zuck hatte gestern erst etwas dazu gepostet und nun hat Googles AlphaGo-AI den professionellen 2nd Dan Go-Spieler Fan Hui („dan ranks are considered master ranks“) geschlagen:

Traditional AI methods—which construct a search tree over all possible positions—don’t have a chance in Go. So when we set out to crack Go, we took a different approach. We built a system, AlphaGo, that combines an advanced tree search with deep neural networks. These neural networks take a description of the Go board as an input and process it through 12 different network layers containing millions of neuron-like 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 trained the neural networks on 30 million moves from games played by human experts, until it could predict the human move 57 percent of the time (the previous record before AlphaGo was 44 percent). But our goal is to beat the best human players, not just mimic them. To do this, AlphaGo learned to discover new strategies for itself, by playing thousands of games between its neural networks, and adjusting the connections using a trial-and-error process known as reinforcement learning. Of course, all of this requires a huge amount of computing power, so we made extensive use of Google Cloud Platform.

After all that training it was time to put AlphaGo to the test. First, we held a tournament between AlphaGo and the other top programs at the forefront of computer Go. AlphaGo won all but one of its 500 games against these programs. So the next step was to invite the reigning three-time European Go champion Fan Hui—an elite professional player who has devoted his life to Go since the age of 12—to our London office for a challenge match. In a closed-doors match last October, AlphaGo won by 5 games to 0. It was the first time a computer program has ever beaten a professional Go player. You can find out more in our paper, which was published in Nature today.