Reinforcement Learning Methods for tic-tac-toe

Visulization for Learned Q values

This project involves implmenation and comparison for tabular Q-learning and Deep Q-learning for the game tic-tac-toe. Additionally, stratagy such as self-learning and learning from experts have also been comparied. We also experiments with various training parameters.

Yanbo Xu
Yanbo Xu

My current research interests are computer vision and robotics.