This repo is a collection of Jupyter notebooks I’m building while learning reinforcement learning. It serves both as a backup of real-time experiments in my own study and a public learning resource.
These notebooks are written in Python and focus on experimenting with common RL concepts and algorithms alongside the theoretical RL learning process. They’re not polished or complete — just a way to test ideas, explore theory, and keep track of progress. I’m sharing them here in case they’re useful or interesting to others who are also learning RL.
Contributions are welcome — whether it’s fixing code, improving coding style, adding explanations, or sharing new ideas. The goal is to build a helpful resource together for the wider community.
Thanks to the researchers and authors who laid the foundations of reinforcement learning.
Special appreciation goes to Richard S. Sutton and Andrew G. Barto for their influential contributions to the field.