Favodar/Reinforcement-Learning

Source code for the website "Quick Introduction To Reinforcement Learning" and accompanying Jupyter Notebook and python code example for policy iteration.

Reinforcement-Learning

Source code for the website "Quick Introduction To Reinforcement Learning" and accompanying Jupyter Notebook and python code example for policy iteration.

The "docs" folder contains the html, css and js files for the website which is hosted via GitHub pages.

The "Jacks-Car-Rental" folder contains the Jupyter Notebook files. There you can also access the code of "CarRentalEnvironment", which is my implementation of the environment (a Markov decision process) described in the "Jack's Car Rental" excercise in "Reinforcement Learning: An Introduction".