A Free course in Deep Reinforcement Learning from beginner to expert.


Some of the agents you'll implement during this course:

Deep Reinforcement Learning Course

This course is a series of articles and videos where you'll master the skills and architectures you need, to become a deep reinforcement learning expert.

You'll build a strong professional portfolio by implementing awesome agents with Tensorflow and PyTorch that learns to play Space invaders, Minecraft, Starcraft, Sonic the hedgehog and more!







The Foundations Syllabus

The course is currently updating to v2, the date of publication of each updated chapter is indicated.



Chapter 1: Introduction to Deep Reinforcement Learning V2.0


In this first chapter, you'll learn all the essentials concepts you need to master before diving on the Deep Reinforcement Learning algorithms.


📜 Chapter: V2.0


📹 Video version: V2.0


📚 More ressources:



Chapter 2: Q-Learning V2.0


Part 1 V2.0

In this chapter, you’ll dive deeper into value-based-methods, learn about Q-Learning, and implement our first RL agent which will be a taxi that will need to learn to navigate in a city to transport its passengers from point A to point B 🚖


📜 Course: V2.0

📹 Video: V2.0


📚 More resources:


Part 2 📅10/23 📅



Chapter 3: Deep Q-Learning V1 V2: 📅TBA 📅 V2 👨‍💻: We will build an agent that learns to play Space Invaders 👾


You'll learn the Deep Q Learning algorithm and how to implement it with Tensorflow and PyTorch.

📜 Course: V1



👨‍💻 An Agent that plays Doom and kill enemies

Doom


📹 Video: V1

👨‍💻 Create an Agent that learns to play Atari Space Invaders


📚 More resources:



Chapter 4: Improvements in Deep Q Learning V1 V2: 📅TBA📅 V2 👨‍💻: We will build an agent that learns to play Doom.


In this chapter, you'll learn the latests improvments in Deep Q Learning (Dueling Double DQN, Prioritized Experience Replay and fixed q-targets) and how to implement them with Tensorflow and PyTorch.

📹 Video: V1

👨‍💻 Create an Agent that learns to play Doom Deadly corridor




Chapter 5: Policy Gradients V1 V2: 📅TBA📅


In this chapter you'll learn about Policy gradients and how to implement it with Tensorflow and PyTorch.

📜 Course: V1



👨‍💻 An Agent that learns to survive in an hostile environment in Doom

Doom Health


📹 Video: V1

👨‍💻 Create an Agent that learns to play Doom deathmatch





Chapter 6: Advantage Actor Critic (A2C) and Asynchronous Advantage Actor Critic (A3C) V1 V2: 📅TBA📅


You'll learn the Actor Critic's logic and how to implement an A2C agent that plays Sonic the Hedgehog with Tensorflow and PyTorch.

📜 Course: V1



👨‍💻 Create an Agent that learns to play Sonic the Hedgehog

Sonic the Hedgehog

📹 Video: V1



📚 More resources:



Chapter 7: Proximal Policy Gradients V1 V2: 📅TBA📅


You'll learn PPO how to implement it with Tensorflow and PyTorch.

📹 Video: V2: 📅TBA📅


Chapter 8: Curiosity-Driven Learning through Next State Prediction V1 V2: 📅TBA📅


📜 Course: V1

Super Mario Bros

📹 Video: V2: 📅TBA📅


Chapter 9: Random Network Distillation: a new take on Curiosity-Driven Learning V1 V2: 📅TBA📅


📹 Video: V2: 📅TBA📅


Chapter 10: Introduction to Unity ML-Agents V1 V2: 📅TBA📅


📜 Course: V1



👨‍💻 Train a reinforcement learning agent to jump over walls.

UnityML Wall Jump

📹 Video: V1


Chapter 11: Diving deeper into Unity-ML Agents V1 V2: 📅TBA📅



Chapter 12: Unity-ML Agents: The Mayan Adventure V1 V2: 📅TBA📅


📜 Course:



👨‍💻 Train an agent to get the golden statue in this dangerous environment.

The Mayan Adventure

📹 Video:V1


How to help?


👏 and 👍

Clap our articles and like our videos a lot

Clapping in Medium means that you really like our articles. And the more claps we have, the more our article is shared

Liking our videos help them to be much more visible to the deep learning community

Share and speak about our articles and videos

By sharing our articles and videos you help us to spread the word.



Keep in touch!