Our CS 221 project which is about developing an Abalone game-playing agent.
This repository includes:
- Paper.pdf => the final paper for the project
- abaloneGUI => a GUI to play and see the progress of the game
- alphabeta.py => includes an implementation of minimax with AlphaBeta pruning and all of the other additions to make the seearch faster and more efficient. This is the program that you will want to run to play the game.
- learnedWeights.py => file that has the weights that were learned from TD-learning. These are the weights that we refer to in our paper.
- minimax.py => a prelimenary agent that uses only Minimax (this will take an extremely long time to play)
- model.py => the game infrastructure
- tdlearning.py => our implementation of TD-learning
A helpful visualization of our axises representation can be found at https://www.redblobgames.com/grids/hexagons/?fbclid=IwAR2PEBkrOX6G4KndR9Fl10_pIhjqpLbtOt80BYnanxaQ8CHLsdieZdvlkEE#distances