RL Lab

Ten lessons taking you from curve fitting to policy gradients, each with a live in-browser demo.

Lessons

1. Lesson 1 - Neural Networks & Curve Fitting Oct 2025
2. Lesson 2 - Decision Boundaries Oct 2025
3. Lesson 3 - Optimizer Showdown Oct 2025
4. Lesson 4 - Convolutional Networks Oct 2025
5. Lesson 5 - Deeper Convolutions Oct 2025
6. Lesson 6 - Autoencoders & Latent Space Nov 2025
7. Lesson 7 - Neural Painter Nov 2025
8. Lesson 8 - Deep Q-Networks Nov 2025
9. Lesson 9 - Inverted Pendulum Nov 2025
10. Lesson 10 - Policy Gradients Nov 2025

Live Demos