Diving into Deep RL with Hugging Face

I'm stoked to be diving headfirst into the world of Deep Reinforcement Learning (DRL) using the awesome course from Hugging Face. This is my python implementation of the Hugging Face Reinforcement Learning tutorial.

Course

Here is the link that you need to access to Hugging Face's tutorial:

Course Link: Hugging Face Deep RL Course

Repository Link: Hugging Face Deep RL Repository

Check Your Progress: Hugging Face Check My Progress

Summary

This course is going to walk me through the key ideas:

• Reinforcement Learning Basics: Covering the fundamentals like how agents learn by interacting with their environment and the math behind it all (like those fancy Markov Decision Processes).
• Powerful Algorithms: Learning about different approaches like Q-learning and those slick Policy Gradient methods.
• Deep Learning Power-Ups: Seeing how deep neural networks supercharge these algorithms, making it possible to solve really complex problems.
• Hands-on Training: The best part! Training agents in cool environments and use libraries like Stable Baselines3 to make things easier.

Basically, I'm going to learn how to build intelligent agents that can learn to do amazing things! I can't wait to share what I learn along the way.

In a nutshell: This course is going to give me the skills and knowledge to build awesome DRL agents. Let's do this!

Table of Contents

Units

1. Train your first Deep Reinforcement Learning Agent
2. Introduction to Q-Learning
3. Deep Q-Learning with Atari Games
4. Policy Gradient with Pytorch
5. An Introduction to Unity ML-Agents
6. Actor Critic Methods with Robotics Environments
7. Introduction to Multi-Agents and AI vs AI
8. Proximal Policy Optimisation (PPO) Part I
9. Proximal Policy Optimisation (PPO) Part II

Bonus

1. Introduction to Deep Reinforcement Learning with Huggy
2. Automatic Hyperparameter Tuning with Optuna
3. Advanced Topics In Reinforcement Learning
4. Imitation Learning With Godot RL Agents

More Ressources

Also, if you are realy interested into reinforcement learning, you should consider these ressources:

Books

• Reinforcement Learning An Introduction second edition
  by Richard S. Sutton and Andrew G. Barto.
• Grokking Deep Reinforcement Learning
  by Miguel Morales
• Multi-Agent Reinforcement Learning: Foundations and Modern Approaches
  by Stefano V. Albrecht, Filippos Christianos, Lukas Schäfer
• Reinforcement Learning and Stochastic Optimization: A Unified Framework for Sequential Decisions
  by Warren B. Powell
• Algorithms for Reinforcement Learning
  by Csaba Szepesvari
• Bandit Algorithms
  by Tor Lattimore and Csaba Szepesvári
• Reinforcement Learning and Optimal Control
  by Dimitri Bertsekas

Websites

• OpenAI Spinnning Up
• Berkeley’s Deep RL Bootcamp
• Berkeley’s Deep Reinforcement Learning course
• David Silver's Course
• Lilian's blog
• Pytorch's tutorial
• Pytorch lightning's tutorial

Repositories

• Clean RL
• RL in the real world
• Denny Britz's Github