/Understanding-Reinforcement-Learning-Hands-On

This is a repository that goes hand by hand with my Medium Series under the same name. Here, each article will be further developed, with fully working coding solutions.

Primary LanguageJupyter Notebook

Understanding-Reinforcement-Learning-Hands-On

This is a repository that goes hand by hand with my Medium Series under the same name. Here, each article will be further developed, with fully workable coding solutions.

Contents

Here is a list of all the articles and their respective notebooks to follow along.

  1. Introduction

  2. Multi-Armed Bandits - Notebook

  3. Non-Stationarity - Notebook

  4. Markov Decision Processes - Notebook

Dependencies

This is a list of all the libraries used throughout the repository. They are required for running the examples.

  • Numpy
  • Matplotlib
  • Gym
  • Tqdm