AlphaGo
Last updated
Last updated
Go is an ancient board game with a rich history. It's believed to be the oldest board game continuously played to present day. It was invented in China, more than 2500 years ago. Go was considered one of the four essential arts of the cultured aristocratic Chinese scholars in antiquity. (Wikipedia)
What interesting is that the number of possible moves and counter moves makes it more complex than chess. the number of possible board positions in Go is approximately 2.1 * 10^170
In other words... the same "brute-force" approach used by super computers to beat humans in chess will no longer work. Something fundamentally different is needed.
October 2015 - AlphaGo defeated the European Go champion FanHui
March 2016 - AlphaGo defeated Lee Sedol, one of the best players at Go
October 2017 AlphaGo Zero, a version trained without human data beat AlphaGo
December 2017 a generalized version called AlphaZero achieved within 24 hours superhuman level of play in games of chess, shogi and Go
With the 37th move in the match's second game, AlphaGo landed a surprise on the right-hand side of the 19-by-19 board that flummoxed even the world's best Go players, including Lee Sedol. "That's a very strange move," said one commentator, himself a nine dan Go player, the highest rank there is. "I thought it was a mistake," said the other. Lee Sedol, after leaving the match room, took nearly fifteen minutes to formulate a response. Fan Gui---the three-time European Go champion who played AlphaGo during a closed-door match in October, losing five games to none---reacted with incredulity. But then, drawing on his experience with AlphaGo---he has played the machine time and again in the five months since October---Fan Hui saw the beauty in this rather unusual move.
Indeed, the move turned the course of the game. AlphaGo went on to win Game Two, and at the post-game press conference, Lee Sedol was in shock. "Yesterday, I was surprised," he said through an interpreter, referring to his loss in Game One. "But today I am speechless. If you look at the way the game was played, I admit, it was a very clear loss on my part. From the very beginning of the game, there was not a moment in time when I felt that I was leading. Wired: In Two Moves, AlphaGo and Lee Sedol Redefined the Future
So first there was an algorithm that could beat the best human player, showed something that is as close to brilliant intuition as it gets... and was trained on previous human played games (Go has a written history dating back centuries). then came a version called "zero" because it received zero training, it learned by playing itself - and it beat the previous version. And then came the generalized zero version that can do the same thing for other games.
You can watch the full award winning documentary on YouTube