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 with Tensorflow

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 that learns to play Space invaders, Doom, Sonic the hedgehog and more!








Step 1: What is Deep Reinforcement Learning?


You'll learn all the essentials concepts you need to master before diving on the Deep Reinforcement Learning algorithms.

  • What’s Deep Reinforcement Learning and what is its process?
  • Why rewards is the central idea in RL?
  • What’s the 3 approaches of Reinforcement Learning?


πŸ“š More ressources:


Step 2: Q-Learning


πŸ“œ Course:

You'll learn the Q-learning algorithm and how to implement it with Numpy.



πŸ‘¨β€πŸ’» Create an Agent that learns to play FrozenLake

FrozenLake


πŸ“Ή Video:

You'll learn how to implement the Q-learning algorithm with Numpy.

πŸ‘¨β€πŸ’» Create an Agent that learns to play Taxi-v2


πŸ“š More resources:



Step 3: Deep Q-Learning


πŸ“œ Course:

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



πŸ‘¨β€πŸ’» An Agent that plays Doom and kill enemies

Doom


πŸ“Ή Video:

πŸ‘¨β€πŸ’» Create an Agent that learns to play Atari Space Invaders

πŸ“š More resources:



Step 3+: Improvements in Deep Q Learning


πŸ“œ Course:

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.




πŸ“Ή Video:

You'll learn the latests improvements in Deep Q Learning (Dueling Double DQN, Prioritized Experience Replay and fixed q-targets) and how to implement them with Tensorflow.

πŸ‘¨β€πŸ’» Create an Agent that learns to play Doom Deadly corridor




Part 4: Policy Gradients


πŸ“œ Course:

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



πŸ‘¨β€πŸ’» An Agent that learns to survive in an hostile environment in Doom

Doom Health


πŸ“Ή Video:

πŸ‘¨β€πŸ’» Create an Agent that learns to play Doom deathmatch





Part 5: Advantage Actor Critic (A2C) and Asynchronous Advantage Actor Critic (A3C)


πŸ“œ Course:

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




πŸ“Ή Video:

πŸ‘¨β€πŸ’» Create an Agent that learns to play Sonic the Hedgehog

Sonic the Hedgehog

πŸ“š More resources:



Part 6: Proximal Policy Gradients in A2C style


πŸ“œ Course:

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





Sonic the Hedgehog 3


Part 7: Curiosity Driven Learning

πŸ“… September

TBA



How to help?


3 ways:

πŸ‘ and πŸ‘

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.

πŸ‘¨β€πŸ’»

Publish your own implementations.

Show us what you've learned!


Keep in touch!