AI agent for the game of Dots and Boxes made by Wouter Baert (@Wout12345) and Stijn Caerts (@StijnCaerts). This project was made as an assignment for the course Machine Learning: Project at KU Leuven in 2018. Our implementation of the AI agent was the third best submission of the course.
- Clone the repo with
git clone --recurse-submodulesto load the submodule.
- Y. Zhuang, S. Li, T. V. Peters and C. Zhang, "Improving Monte-Carlo tree search for dots-and-boxes with a novel board representation and artificial neural networks," 2015 IEEE Conference on Computational Intelligence and Games (CIG), Tainan, 2015, pp. 314-321.
- Prince, Jared, "Game Specific Approaches to Monte Carlo Tree Search for Dots and Boxes" (2017). Honors College Capstone Experience/Thesis Projects. Paper 701.
- Q-Learning for a Simple Board Game
- Solving Dots-And-Boxes
