Many of the files in this repository are original to https://github.com/sfujim/TD3 - the code from the original authors of TD3, the learning algorithm we utilize in our notebooks here.
The exercises (notebooks) in this repo comprise a short course that introduces the practical considerations needed to effectively apply reinforcement learning to real-world problems.
See the Jupyter Book for a static version of the course, or to work through the course for yourself, you can run the notebooks.