RLConnect - Reinforcement Learning agent to play Dots and Boxes

Introduction

This project is being done in Autumn 2020 semester and expected date of completion is 15th December 2020. We attempt to experiment with RL algorithms to automate Dots and Boxes, a popular high-school pen and paper game.

Approach

We make a web-based GUI (link to be available soon) to interface with players and develop an underlying python-based agent to make decision based on the state of the game. We are going to experiment with various algorithms including Q-learning, DQN and SARSA.