This is a notebook that implement Tic Tac Toe game with use of the Monte-Carlo tree search (MCTS) algorithm. This is part of the Reinforcement Learning course of E. LePennec, professor at École Polytechnique.
Alexis Gerbeaux et Cédric Allain - février 2020
Sources:
- Tic Tac Toe game: https://gist.github.com/eaorak/3966315
- MCTSPY package: https://pypi.org/project/mctspy/