A Reinforcement Learning course by Andrew Ng? | Coursera Community
Coursera Header

A Reinforcement Learning course by Andrew Ng?

  • 3 April 2019
  • 14 replies

Userlevel 5
Coursera has the most reputable online training in Machine Learning (from Stanford U, by Andrew Ng), a fantastic Deep Learning specialization (from deeplearning.ai, also by Andrew Ng) and now a practically oriented TensorFlow specialization (also from deeplearning.ai).

But it has very little offering in Reinforcement Learning, where Coursera clearly lags competition, even though it is hard to find quality online courses for a non-ridiculous price elsewhere. David Silver's recorded lectures at UCL are first class, as is Sutton and Barto's fantastic book, but this is not the same as a coursework with lessons, quizzes, exercises, assignments and perhaps a certificate in the end. Competitors offer online courses and nano-degrees, but it is hard to assess the quality of the teachers and material, and the cost is sometimes unreasonable, to say the least.

I really hope that Coursera will soon produce a specialization up to Andrew Ng's standard on RL, as this is currently and very visibly missing from its catalog. If it was taught by Andrew Ng in person, I would sign up immediately, no questions asked, as, I think, would the thousands of others who followed his offerings in ML and DL.

14 replies

Userlevel 7
Thanks for this thoughtful suggestion, @antoinesavine. I'm tagging our data science content strategy expert @Vidisha here, too.
Userlevel 7
Badge +6
Hello everyone,

I'm interested in this topic, and I suggest to design an introductory course on RL at Coursera, especially after I checked the autonomous helicopter flight project by Stanford University:
autonomous helicopter flight project
followed by the paper published by Andrew Ng describing the project:
Autonomous helicopter flight via reinforcement learning
Userlevel 7
Thanks, @Mo Rebaie! Make sure you vote for @antoinesavine's course suggestion (if you haven't already).
Userlevel 7
Badge +6
Thank you, I already did it.
So much hunger looking for prof Ng to start RL courses, there are a few online, like deep RL bootcamp, but without assignment, it is hard to learn.
Userlevel 1
Badge +2

catjohn is right. Without an assignment or a project, it is extremely difficult for people like us to learn. 

Userlevel 1
Badge +2

I hope Andrew Ng will see this post and know there are many people here who want him to teach deep learning. It is just like that Quote: “Do you want to sell sugar water or change the world?”


Deep reinforcement learning may even better.


Andrew’s courses are awesome. Been looking forward to an RL course since I completed Andrew Ng’s ML course years ago.


A related problem is that there are virtually no applied RL books besides the opportunistic offerings by a publisher that will print anything so long as it has a hot title.  And even a decent book like that by Maxim Lapan suffers from Python code that is difficult to get running because the required libraries don’t all load. So you spend most of the time on stackoverflow.com looking for workarounds.

So the ideal Andrew Ng course would supplement the excellent video presentations with server-based Jupyter worksheets for doing  the assignments plus “handouts” that would encapsulate key concepts.

And so long as the price was not outlandish, I think there would be a huge number of subscribers.


Badge +1

I just noticed that Maxim Lapan’s book Deep Reinforcement Learning Hands-On has a 2nd edition coming out on January 9th, 2020, so even though I haven’t read it like @RickSG has, it might be a good choice until Andrew builds a class

Here’s the link:



Also, a course on Adversarial Networks would complete the whole package and Coursera would become the one-stop shop for learning the basics of Deep Learning of the most fascinating topics that are of high relevance today. Andrew NG has already transformed my life through his teachings and I pray that he himself would instruct the rest of the courses from deeplearning.ai.



Coursera offers a Specialization on Reinforcement Learning by University of Alberta since a few weeks ago. I am currently on the third course and enjoying the course. I also would enjoy a course on RL by Andrew Ng, but I  think this other  course might be worth looking at.

Regarding resources on RL, I did enjoy reading Maxim Lapans book and was able to get the code running (this was in March - June). Another useful ressource might be Open AI’s Spinning Up: https://spinningup.openai.com/en/latest/


Best regards,



Userlevel 7

Hi everyone! I’ve shared your feedback with our content strategy team – thank you. Did you know we launched a Reinforcement Learning Specialization in July? It’s taught by the University of Alberta and the Alberta Machine Intelligence Institute (not Andrew Ng) and it has great reviews. The Specialization includes four courses:

Fundamentals of Reinforcement Learning

Sample-based Learning Methods

Prediction and Control with Function Approximation

A Complete Reinforcement Learning System (Capstone)