Reinforcement Learning tutorial

By:

Juan Pablo Martínez Piazuelo

Daniel Esteban Ochoa Tamayo

This tutorial is organized as follows:

• Part 0: python/numpy introduction.
• Part 1: tabular Q-learning (gridworld).
• Part 2: Double Deep Q-learning (gridworld).
• Part 3: Deep Deterministic Policy Gradient (continous control) (under developement).

The files of the tutorial are under the folder numpy-based

Launch tutorial:

With binder (recommended):

With Azure notebooks: