Reinforcement Learning Labs

A 6-part notebook series introducing reinforcement learning concepts and methods.

• Start here: Part 0 and read in order.
• Each chapter is a rendered Jupyter notebook (static).

Chapters

• Part 0: Basic Probability Simulations
• Part 1: Prediction and Control
• Part 2: Multi-Armed Bandits
• Part 3: Dynamic Programming
• Part 4: Monte Carlo Methods
• Part 5: Temporal Difference Learning