Reinforcement Learning from Scratch

A notebook series introducing the fundamentals of reinforcement learning alongside implementations of algorithms, from bandits to deep learning.

📂 Repository Structure

1. Introduction to RL - Bandits, Actions, Rewards

• 1.1 Agents, Rewards, and Actions

2. Markov Decision Processes and Dynamic Programming

• 2.1 MDPs, States, Policies and Dynamic Programming
• 2.2 Introducing Randomness

3. Monte Carlo Methods

• 3.1 Monte Carlo Methods

4. Temporal Difference Methods

Coming soon

5. Deep Reinforcement Learning

Coming soon

📚 References

This series loosely follows the structure of Reinforcement Learning: An Introduction by Sutton & Barto.