ALPHAGO - THE FIRST COMPUTER PROGRAM

TO EVER BEAT A PROFESSIONAL PLAYER AT GO

Match Begins!
https://deepmind.com/alpha-go.html

The Google DeepMind challenge match starts later today in Seoul, South Korea at
13:00 KST; 04:00 GMT-1 day (8th March) 20:00 PT, 23:00 ET. Tune in live.

For updates each day on the Google DeepMind Challenge Match of AlphaGo vs Lee
Sedol, please follow theGoogle APAC blog and the DeepMind YouTube channel.

Match Details

In October 2015, our program AlphaGo won 5-0 in a formal match against the reigning
3-times European Champion, Fan Hui, to become the first program to ever beat a
professional Go player in an even game.

Now AlphaGo will face its ultimate challenge: a 5-game challenge match in Seoul
against the legendaryLee Sedol, the top Go player in the world over the past decade.
For full details, please see our press release.

The matches will be held at the Four Seasons Hotel, Seoul, South Korea, starting at 1pm
local time
(4am GMT; day before 11pm ET, 8pm PT) on March 9th, 10th, 12th, 13th and 15th.

The matches will be livestreamed on DeepMinds YouTube channel as well as

broadcast on TV throughout Asia through Koreas Baduk TV, as well as in China, Japan,
and elsewhere.

Match commentators will include Michael Redmond, the only professional Western Go
player to achieve
9 dan status. Redmond will commentate in English, and Yoo Changhyuk professional 9
dan, Kim Sungryong professional 9 dan, Song Taegon professional 9 dan, and Lee
Hyunwook professional 8 dan will commentate in Korean alternately.

The matches will be played under Chinese rules with a komi of 7.5 (the compensation
points the player who goes second receives at the end of the match). Each player will
receive two hours per match with three lots of 60-second byoyomi (countdown periods
after they have finished their allotted time).
Each match is expected to take around 4-5 hours.

Nature Paper Details

Our Nature paper published on 28th January 2016, describes the technical details
behind a new approach to computer Go that combines Monte-Carlo tree search with
deep neural networks that have been trained by supervised learning, from human expert
games, and by reinforcement learning from games of self-play.
The game of Go is widely viewed as an unsolved grand challenge for artificial
intelligence. Despite decades of work, the strongest computer Go programs still only
play at the level of human amateurs. In this paper we describe our Go program,
AlphaGo. This program was based on general-purpose AI methods, using deep neural
networks to mimic expert players, and further improving the program by learning from
games played against itself. AlphaGo won over 99% of games against the strongest
other Go programs. It also defeated the human European champion by 50 in an official
tournament match. This is the first time ever that a computer program has defeated a
professional Go player, a feat previously believed to be at least a decade away.

AlphaGo: using machine learning to master the ancient game of Go

January 27, 2016
https://googleblog.blogspot.com.br/2016/01/alphago-machine-learning-game-go.html

The game of Go originated in China more than 2,500 years ago. Confucius wrote about the
game, and it is considered one of the four essential arts required of any true Chinese
scholar. Played by more than 40 million people worldwide, the rules of the game are simple:
Players take turns to place black or white stones on a board, trying to capture the opponent's
stones or surround empty space to make points of territory. The game is played primarily
through intuition and feel, and because of its beauty, subtlety and intellectual depth it has
captured the human imagination for centuries.

But as simple as the rules are, Go is a game of profound complexity. There are
1,000,000,000,000,000,000,000,000,000,000,000,000,000,000,000,000,000,000,000,000,000,0
00,000,000,000,000,000,000,000,000,000,000,000,000,000,000,000,000,000,000,000,000,000,
000,000,000,000,000,000,000,000,000,000,000,000,000,000 possible positionsthats more
than the number of atoms in the universe, and more than a googol times larger than chess.

This complexity is what makes Go hard for computers to play, and therefore an irresistible
challenge to artificial intelligence (AI) researchers, who use games as a testing ground to invent
smart, flexible algorithms that can tackle problems, sometimes in ways similar to humans. The
first game mastered by a computer was noughts and crosses (also known as tic-tac-toe) in
1952. Then fell checkers in 1994. In 1997 Deep Blue famously beat Garry Kasparov at chess.
Its not limited to board games eitherIBM's Watson [PDF] bested two champions at Jeopardy
in 2011, and in 2014 our own algorithms learned to play dozens of Atari games just from the raw
pixel inputs. But to date, Go has thwarted AI researchers; computers still only play Go as well as
amateurs.

Traditional AI methodswhich construct a search tree over all possible positionsdont 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 ofGoogle 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 Huian elite professional player who has devoted his life to Go
since the age of 12to 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.

Whats next? In March, AlphaGo will face its ultimate challenge: a five-game challenge match in
Seoul against the legendary Lee Sedolthe top Go player in the world over the past decade.

We are thrilled to have mastered Go and thus achieved one of the grand challenges of AI.
However, the most significant aspect of all this for us is that AlphaGo isnt just anexpert
system built with hand-crafted rules; instead it uses general machine learning techniques to
figure out for itself how to win at Go. While games are the perfect platform for developing and
testing AI algorithms quickly and efficiently, ultimately we want to apply these techniques to
important real-world problems. Because the methods weve used are general-purpose, our hope
is that one day they could be extended to help us address some of societys toughest and most
pressing problems, from climate modelling to complex disease analysis. Were excited to see
what we can use this technology to tackle next!
Posted by Demis Hassabis, Google DeepMind