Othello is a board game involving abstract strategy and played by two players on a board with 8 rows and 8 columns and a set of distinct pieces for each side. Pieces typically are disks with a light and a dark face, each side belonging to one player. The player's goal is to have a majority of their colored pieces showing at the end of the game, turning over as many of their opponent's pieces as possible.
This project is the first step for me in the Data Science and AI field, where I would like to work in the future.
The par excellence choice for this kind of project is to recreate Chess or Connect-4, but I have two problems with the latter. I found the first one difficult ot realize (it is necessary to recognize its weaknesses). Furthermore, the Internet provides a lot of complete implementations and full tutorial walkthroughs for both of them (and it is tempting to look at an already built solution).
So I decided to choose one of my childhood games: Othello (anciently called Reversi). The rules are simple to understand (if you never try, give it a go), but it has this reputation of "easy to learn, hard to master", which seemed to be a good idea to create an intelligence playing to it.
- Game mechanisms
- Game graphics
- Minimax algorithm
- Basic
- αβ-pruning
- Genetic-weighted evaluation
- Convolutional Neural Network
- Temporal Difference Learning
- Website with all intelligence modes
Distributed under the MIT License. See LICENSE.txt for more information.
Causse, B., Nicolet, S., & Delorme, R. (2015). Algorithmes (ou comment pensent Les ordinateurs). Fédération Française d'Othello. Retrieved March 2, 2022, from https://www.ffothello.org/informatique/algorithmes/.
Oliviera, A. (2021, October). Othello Games. Retrieved March 2, 2022, from https://www.kaggle.com/andrefpoliveira/othello-games.
Sannidhanam, V., & Annamalai, M. (2004, November 11). An Analysis of Heuristics in Othello. Retrieved March 2, 2022, from https://courses.cs.washington.edu/courses/cse573/04au/Project/mini1/RUSSIA/Final_Paper.pdf.