Reinforcement Learning with TensorFlow

Go versus chess

In 1997, IBM's DeepBlue defeated the then world champion Gary Kasparov in the game of chess. Almost two decades later, Google DeepMind's AI program AlphaGo defeated the 9-dan Go player and former world champion Lee Sedol. In order to understand the giant leap and achievement of Google DeepMind through AlphaGo, let's first understand the difference between these two games and then the architecture used behind the AI of DeepBlue and AlphaGo.

Both chess and Go need two players. In chess, each player has sixteen pieces that are of six different types possessing different strengths as per the game rules. The goal is to capture the opponent's King. On the other hand, Go starts with a blank board where each player places a stone ...