Oct 3, 2020
Launching Deep Reinforcement Learning Course v2.0
A free course in Deep Reinforcement Learning from beginner to expert.
🎉 I’m happy to announce the launch of the new version of the Deep Reinforcement Learning Course 🥳, a free course from beginner to expert where you learn to master the skills and architectures you need, to become a deep reinforcement learning expert with Tensorflow and PyTorch.
Since the launch of the first version in 2018, we had more than 40,000 claps, 2,500 GitHub stars.
Since then, a lot of breakthroughs happened in Deep RL. New libraries were published and some of our implementations become obsolete. That’s why, in order to keep up the pace of the breakthrough, we publish this new version.
In addition to the foundations syllabus, we add a new series on building AI for videos games in Unity and Unreal Engine using Deep RL.
What this new version will look like?
The Foundations
The foundations will be composed of 10 chapters each about an architecture or a topic, each of them will be an article and a video.
You can check the syllabus on the Deep Reinforcement Learning Course’s website.
- Introduction to Reinforcement Learning
- Q-Learning
- Deep Q-Learning
- Improvements in Deep Q-Learning
- Policy Gradients Methods
- Actor Critic Methods (A3C, A2C)
- Proximal Policy Optimization (PPO)
- Soft-Actor Critic (SAC)
- Curiosity Driven Learning
- Curiosity through Random Network Distillation
- …
As for the first version, for each chapter, we will explain deeply the topic and the mathematical details behind it.
And then, we’ll dive on a complete implementation of the agent with Tensorflow and PyTorch.
The chapters will be published on this blog, don’t forget to follow it:
The videos version will be published on Youtube, don’t forget to subscribe:
You can check the syllabus in the official Deep Reinforcement Learning Course’s website.
New implementations
A new course, means new implementations, this time we will use 2 libraries: TensorFlow 2.0 and PyTorch.
And we will use new environments:
- Unity ML-Agents
- Minecraft (MineRL)
- Super Mario Bros, Sonic the Hedgehog (OpenAI Retro)
- Doom (Vizdoom)
- Starcraft
- …
Case studies
In addition to the foundations of deep reinforcement learning, we will study how to implement AI in real video games using Deep RL.
To do that, we’re going to use 2 game engines:
The idea will be to create AI for different type of games created in Unity and Unreal Engine. From FPS (First Person Shooter), simulations … to casual games.
What’s the schedule?
The pace is 2 videos/articles per week:
One video and its associated article on Tuesday
One on Saturday
Again, to be sure to not miss any of the new chapters and videos, don’t forget to:
Subscribe to our Youtube Channel
How to help ?
If you want to help us, please like, share, and speak about our articles and videos. By sharing our articles and videos you help us to spread the word.
Back in April 2018 when I launched my first article about Introduction to RL I didn’t know that it will become one of the biggest RL courses online and a GitHub repository with 2.400 GitHub stars. For that, I want to thank you . Though I receive a lot of emails every day and unfortunately I can’t reply to all I try to do better everyday on this issue. My apologies to people who didn’t receive any response.
I really hope that you will like this new version of the course. This is made for you. As consequence, we’re always pleased to receive some feedback 📝.
If you liked my article, please click the 👏 below as many time as you liked the article so other people will see this here on Medium. And don’t forget to follow me on Medium and on Youtube.
Keep learning, stay awesome,
