I would like to automate the player 's decisions in classic World War 2 turn based board game, 'Axis and Allies'. The information in the game is at full discolsure, one step requires eleborate planning, the outcome of battles is decided by rolling dice.
The rules of the board game can be downloaded from the homepage of the publisher.
The implementation of the computer player will be made possible on the TripleA platform. Because the coding of the platform is not the main focus of the essay, I will build on the existing achievements of the open source project. This way the computer player can easily be tested against human or computer controlled opponents, even on network.
The open source TripleA platform can be downloaded form the official homepage:
The task is big and difficult, so I will decompose it and use the tools of modern artificial intelligence to solve it. I will use primarily the different learning algorithms to solve and to test on the problem. Including:
- Decision making based on rules
- Reinforcement learning