Using Graph Convolutional Networks and TD($\lambda$) to play the game of Risk
–arXiv.org Artificial Intelligence
Risk is 6 player game with significant randomness and a large game-tree complexity which poses a challenge to creating an agent to play the game effectively. Previous AIs focus on creating high-level handcrafted features determine agent decision making. In this project, I create D.A.D, A Risk agent using temporal difference reinforcement learning to train a Deep Neural Network including a Graph Convolutional Network to evaluate player positions. This is used in a game-tree to select optimal moves. This allows minimal handcrafting of knowledge into the AI, assuring input features are as low-level as possible to allow the network to extract useful and sophisticated features itself, even with the network starting from a random initialisation. I also tackle the issue of non-determinism in Risk by introducing a new method of interpreting attack moves necessary for the search. The result is an AI which wins 35% of the time versus 5 of best inbuilt AIs in Lux Delux, a Risk variant.
arXiv.org Artificial Intelligence
Sep-10-2020
- Country:
- Oceania > Australia (0.05)
- South America (0.04)
- North America (0.04)
- Asia (0.04)
- Africa (0.04)
- Europe
- Switzerland > Basel-City
- Basel (0.04)
- Germany > Hesse
- Darmstadt Region > Darmstadt (0.04)
- Switzerland > Basel-City
- Genre:
- Research Report (0.40)
- Industry:
- Leisure & Entertainment > Games (1.00)
- Technology: