Reinforcement Learning Assignment: WindyGridWorld Environment

This Jupyter Notebook was prepared by the following group members:

1. Lang Kah Chun
2. Yee Qing Wei
3. Sun Qi Yang

Objective

The main objective of this reinforcement learning assignment is to use the OpenAI WindyGridWorld Environment to train a smart agent to maximize the reward.

Summary

We included three different modified WindyGridWorld environments and used several approaches to solve the assignment. Our methodologies and results are documented and analyzed within this notebook.