Reinforcement Learning with TensorFlow

AlphaGo – mastering Go

Traditional AI approaches based on search trees covering all possible position fail in the case of Go. The reason being the enormously huge search space because of 2.08 x 10¹⁷⁰ possible moves and thereby, the difficulty in evaluating the strength of each possible board position. Thus, the traditional brute force approaches fail for the enormous search space of Go.

Therefore, advanced tree search such as Monte Carlo Tree Search with Deep Neural Networks was considered to be the novel approach to capture the intuition that humans use to play the game of Go. These neural networks are convolutional neural networks (CNNs) and take an image of the board, that is, the description of the board and activates it through the series ...