Practical guides for RL practitioners: debugging code, reading papers, and reference material.
Who this course is for and what to expect—level, style, and pacing.
Detailed advice on pacing, prerequisites, exercises, and staying motivated through the RL curriculum.
How to study ML and RL efficiently—spaced practice, active recall, and project-based learning.
What to learn before or alongside reinforcement learning—math, programming, and ML basics.
Create and use a conda environment for the RL curriculum.
Pre-installation check and what you need to run the curriculum code and exercises.
Install the main libraries used in the RL curriculum (and optional Theano/TensorFlow).
Building independence in coding—reading specs, breaking problems down, and trying small steps.
Practice habits, when to peek at the solution, and building a coding routine.
Practical guide to finding and fixing common RL bugs. Includes 5 find-the-bug exercises with solutions.
A practical guide to reading reinforcement learning research papers: structure, notation, and three annotated examples (DQN, PPO, SAC).
Practical reference guides for the RL practitioner.