AlphaGo, a largely self-taught Go-playing AI, last night won the fifth and final game in a match held in Seoul, South Korea, against that country's Lee Sedol. Sedol is one of the greatest modern players of the ancient Chinese game. The final score was 4 games to 1. Thus falls the last and computationally hardest game that programmers have taken as a test of machine intelligence. Chess, AI's original touchstone, fell to the machines 19 years ago, but Go had been expected to last for many years to come. The sweeping victory means far more than the US 1 million prize, which Google's London-based acquisition, DeepMind, says it will give to charity.
Black-and-white pieces occupy spaces on a board during a game of Go, which Google's software engineers say they've taught a computer program to play better than most humans. Google's software engineers have taught a computer program to beat almost any human at an ancient and highly complex Chinese strategy game known as "Go." While computers have largely mastered checkers and chess, Go, considered the oldest board game still played, is far more complicated. There are more possible positions in the game than are atoms in the universe, Google said -- an "irresistible" challenge for the company's DeepMind engineers, who used artificial intelligence to enable the program to learn from repeat games. The Google unit's AlphaGo computer program is much more sophisticated than the IBM-created Deep Blue computer that in 1996 won the first chess game against a reigning world champion, Garry Kasparov.
One of the scientists responsible for AlphaGo, the Google DeepMind software that trounced one of the world's best Go players recently, says the same approach can produce a surprisingly competent poker bot. Unlike board games such as Go or chess, poker is a game of "imperfect information," and for this reason it has proved even more resistant to computerization than Go. Gameplay in poker involves devising a strategy based on the cards you have in your hand and a guess as to what's in your opponents' hands. Poker players try to read the behavior of others at the table using a combination of statistics and more subtle behavioral cues. Because of this, building an effective poker bot using machine learning may be significant for real-world applications of AI.
Between 9 and 15 March 2016, a five game competition took place between Lee Sedol, the second-highest ranking professional Go player, and AlphaGo, a computer program created by Google's DeepMind subsidiary. The competition was high-stake: a prize of one million dollars was put up by Google. How exactly did AlphaGo manage to do it? All I could figure out was that machine learning was involved. Having a PhD in machine learning myself, I decided to go through the trouble and read the paper that DeepMind published on the subject. I will do my best to explain how it works in this blog post. I also read different opinions of how much a big deal this win is, and I will have some things to say about that myself (spoiler: I think it's a pretty big deal). Go and chess are very popular board games, which are similar in some respects: both are played by two players taking turns, and there is no random element involved (no dice rolling, like in backgammon). In 1997, Garry Kasparov was defeated by Deep Blue, a computer program written by IBM, running on a supercomputer. This was the first time that a reigning world chess champion was defeated by a computer program in tournament conditions.