AlphaZero applied to an analog game.

Author(s): Mikhail Simin

Originally published on Towards AI.

Artificial Intelligence, Machine Learning

The majority of turn-based games, that AlphaZero has been applied to, all share one common aspect — they are played on a board with discrete locations for pieces. This is true for Go, Chess, Shogi, and numerous other games.

Source: Free Image by Kristin Hardwick

A board with discrete spaces can be easily represented as a small image. A chessboard would fit into an image of size 8 pixels by 8 pixels. For comparison, the stock photo above is 960 pixels by 640 pixels. Convolutional Neural Network (CNN) was specifically designed to do image analysis. It learns faster than a fully connected… Read the full blog for free on Medium.

Join thousands of data leaders on the AI newsletter. Join over 80,000 subscribers and keep up to date with the latest developments in AI. From research to projects and ideas. If you are building an AI startup, an AI-related product, or a service, we invite you to consider becoming a sponsor.

Published via Towards AI