The algorithm is wrapped into a top-level structure (AZ for AlphaZero). The algorithm applies to any game able to fulfill a specified contract. The contract specifies the description of a game state.

Mini AlphaGo is a simple implementation of deep learning for playing some board games such as Go and Tic-Tac-Toe. This was created for educational purposes and used in some classes at KAIST from 2016 ...