Repository with code used to solve the Ultimate Tic Tac Toe for avaliation of Reinforcement Learning subject in FGV/EMAP MSc. The main objective of this project is to develop and train a model to play Ultimate Tic Tac Toe. Here there are three possible players:
- Human player;
- Random player and;
- Trained player.
The first model is made from user's choices. The second model takes a random movement from the set of possible moves, while the last one try to play perfectly.