Playing the Go Game with Deep Neural Networks and Tree Search


(T) Deep Blue, an IBM supercomputer programmed with brute force analysis, defeated Chess grandmaster Garry Kasparov in 1997 over six games. IBM’s Watson won Jeopardy! in 2011. This week the DeepMind Technologies team in London has published another paper in Nature: Mastering the game of Go with deep neural networks and tree search. DeepMind published a previous paper, a year ago, in the same publication on “human-level control through deep reinforcement learning” applied to playing old good Atari games (for more on that paper read: A Silicon Valley Insider: Playing Games with Reinforcement Learning).

The new algorithms from DeepMind for the Go game are much more sophisticated than the previous ones for the Atari games:

The game of Go has long been viewed as the most challenging of classic games for artificial intelligence owing to its enormous search space and the difficulty of evaluating board positions and moves. Here we introduce a new approach to computer Go that uses ‘value networks’ to evaluate board positions and ‘policy networks’ to select moves. These deep neural networks are trained by a novel combination of supervised learning from human expert games, and reinforcement learning from games of self-play. Without any lookahead search, the neural networks play Go at the level of state-of-the-art Monte Carlo tree search programs that simulate thousands of random games of self-play. We also introduce a new search algorithm that combines Monte Carlo simulation with value and policy networks. Using this search algorithm, our program AlphaGo achieved a 99.8% winning rate against other Go programs and defeated the human European Go champion by 5 games to 0. This is the first time that a computer program has defeated a human professional player in the full-sized game of Go, a feat previously thought to be at least a decade away.”


Note: The picture above is the Go Game – image from Wikipedia.

Copyright © 2005-2016 by Serge-Paul Carrasco. All rights reserved.
Contact Us: asvinsider at gmail dot com.