Tic-Tac-Toe Reinforcement Learning

This project explores how an ML agent trained through reinforcement learning learns how to play Tic-Tac-Toe

Required dependencies

OpenAI Gym
Keras
Keras-RL
Numpy
Pandas

To install the dependencies run pip install -r requirements.txt

Usage

To train the model, run python train_model.py
To play against the pretrained model, run python play_with_model.py

A jupyter notebook outlining the steps that I took can be found here