Watch the course summary

Who is this course designed for?


Data Scientists and Machine Learning engineers, who want to learn the basics of Deep Reinforcement Learning and get familiar with a production-grade Deep RL framework within a short time frame


Managers who want to know how Reinforcement Learning is applied in the industry and have an overview of the standard Deep RL tools

Students in a university-level Machine Learning curriculum who want a hands-on, practical introduction to Deep Reinforcement Learning.



What are the prerequisites?


Familiarity with the basics of Deep Learning

Intermediate knowledge of Python programming


What will you learn?

Chapter 1


In Chapter 1, you will get introduced to Reinforcement Learning and understand its key concepts by analyzing a real-world problem and a case study from the industry.

By the end of this chapter, you will be able to analyze any problem and decide if Reinforcement Learning could be a promising approach to solve it.

Chapter 2


In Chapter 2, you will learn the steps and tools involved in solving learning tasks using Reinforcement Learning.



Chapter 3


In Chapter 3, we will focus on Reinforcement Learning environments.

Deep RL agents are usually trained in simulations and OpenAI Gym's simulation API is the industry standard in RL.

You will get introduced to OpenAI Gym and its API. By the end of this chapter, you will be able to control agents in Gym environments.




Chapter 4


In Chapter 4, we will focus on Deep Reinforcement Learning frameworks. Frameworks have high-quality implementations of Deep RL algorithms so that you don't have to develop them from scratch. After this chapter, you will be able to

  • Explain how Deep RL algorithms work at the high level
  • Use Ray RLlib's implementation of Deep RL algorithms to solve OpenAI Gym environments
  • Choose algorithms (e.g. DQN, PPO, TD3, SAC etc.) appropriately based on the nature of the problem
  • Visualize training and evaluation metrics using Tensorboard
  • Save trained agents and use them later (and even capture videos of live agents)

By the end of this chapter, you will be able to solve most benchmark RL tasks in OpenAI Gym.

Detailed Curriculum*

*Some lessons can be previewed without enrolling

  What's Reinforcement Learning good for?
Available in days
days after you enroll
  Reinforcement Learning Problem Solving: High Level Overview
Available in days
days after you enroll
  Using OpenAI Gym Simulations of Reinforcement Learning Tasks
Available in days
days after you enroll
  Using the Ray RLlib Framework to Solve Reinforcement Learning Problems
Available in days
days after you enroll

Features


Short videos

Bite sized video lessons with no fluff (on an average 6 mins long and rarely over 10 mins).

The whole course can be completed in 4 hours (including exercises).


Closed captions


All videos come with high-quality English subtitles.





Coding exercises


Video lessons and demonstrations are followed by coding challenges whenever possible so that you can put your knowledge to the test.




Course Project

The exercises are part of an overarching project, where we teach a robot how to walk. We will record a video of this agent at the end of the course, making it easy to share your work with others.




Certificate of Completion


You will get a downloadable course completion certificate when you finish the course.

Reviews from our learners


"This course broke down complex RL concepts into small pieces that I could easily understand"


Martin Musiol - Managing Data Scientist, IBM



"Brilliant introduction to RL concepts and how they map to RLlib."


Jules S. Damji - Lead Developer Advocate, Anyscale



"Crisp and concise videos"


Saurabh Bodhe - Machine Learning Research Intern, AMD

"If you wanna learn DRL in a short period of time, this is the course for you"


Mobin Nik khesal - Machine Learning Engineer, DataArt

"I liked the practical approach to the content"


Arturs Bumbieris - Student, Codam College

"The amount of knowledge poured in these videos is incredible!"


Gauransh Kumar - AICrowd

Meet the instructor


  • Dibya Chakravorty is a Senior Python Engineer, working with one of the biggest automotive companies in Germany.
  • He has been programming in Python for 15 years. He co-leads the Python community in Munich, Germany.
  • He is also a DataCamp instructor and has taught 20000+ students in the past.


"Dibya is one of the most fluent Python instructors in the community"


Anton Caceres - Python Software Foundation Fellow

"Dibya's technical expertise is on par with his pedagogy "


Hadrien Lacroix - Data Science Curriculum Manager, Datacamp

"No matter how difficult the topic, Dibya makes sure everyone leaves with a smile"


Olga Kupriyanova, PyLadies Organizer


14-day money-back guarantee


Your purchase is protected by a 14-day money-back guarantee. If the course doesn't meet your needs for any reason, let me know within 14 days of the purchase, and you will get a full refund. No questions asked.

If you have any other questions prior to enrollment, please drop me a message.