README

Content locked

The catalog is public. Reading this content requires approved access.

hw10

Reinforcement Learning: Value Iteration and Q-Learning

Overview

1. Getting Started

1.1 Environment Setup

1.2 Gymnasium Environment Overview

2. Value Iteration on FrozenLake-v1 (50 points)

2.1 Implementation

2.2 Algorithm Pseudocode

2.3 Submission for Value Iteration

3. Q-Learning on FrozenLake-v1 (50 points)

3.1 Implementation

3.2 Submission for Q-Learning

4. Helper Files

test.py

visualize.py

5. Deliverables

6. Grading