RL Crash Course: From Bellman to Bots

If you would like to follow along with the code, you can find the supplementaly code for this module in the reinforcement-learning GitHub repository including instructions for setting up the environment and running the code.

Part 1: Concepts & Mathematical Foundations

In this section, we will establish the intuition behind Reinforcement Learning (RL), understand when to use it (and when not to), and derive the mathematical equations that power modern agents.

Part 2: Building a Custom Environment with Gymnasium

In this section, we transition from theory to practice. We will learn the industry-standard API for RL environments and build a custom simulation of a server room thermostat from scratch.

Part 3: Training with PPO and Advanced Frontiers

In this final section, we will replace our random agent with a state-of-the-art Deep Reinforcement Learning algorithm. We'll train it to perfectly manage our server room, discuss how to tune it, and briefly explore the cutting-edge of RL.