AlphaZero

Code for the project for the course "Reinforcement Learning" taught in 2020/2021 at École polytechnique. Implementation of AlphaZero [1].

The environment for Tic-Tac-Toe is the intellectual property of Kim Jeong Ju and was made available at the following repository:

https://github.com/haje01/gym-tictactoe

## Usage

1. Install the requirements using the requirements.txt file.

   pip install -r requirements.txt

2. A demonstration of the algorithm for the game of Tic-Tac-Toe can be ran with the script demo.py.

   python demo.py

Reference

[1] David Silver, Thomas Hubert, Julian Schrittwieser, Ioannis Antonoglou, Matthew Lai, Arthur Guez, Marc Lanctot, Laurent Sifre, Dharshan Kumaran, Thore Graepel, et al. Mastering chess and shogi by self-play with a general reinforcement learning algorithm. arXiv preprint arXiv:1712.01815, 2017.