This project implements a tic-tac-toe agent using different RL algorithms such as value iteration, policy iteration and Q-learning.
- Value iteration: #wins ≥98%
- Policy iteration: #wins ≥94%
- Q-learning: #wins ≥96%
-
Install Python from https://www.python.org/downloads/release/python-380/.
-
Run the following:
$ pip3 install numpy $ pip3 install scipy $ pip3 install pygame
-
In each of the folders in the project, run main.py to execute the program:
$ python main.py