Chevron Left
Back to Introduction to Reinforcement Learning in Python

Learner Reviews & Feedback for Introduction to Reinforcement Learning in Python by Coursera Project Network

36 ratings
7 reviews

About the Course

In this project-based course, we will explore Reinforcement Learning in Python. Reinforcement Learning, or RL for short, is different from supervised learning methods in that, rather than being given correct examples by humans, the AI finds the correct answers for itself through a predefined framework of reward signals. In this course, we will discuss theories and concepts that are integral to RL, such as the Multi-Arm Bandit problem and its implications, and how Markov Decision processes can be leveraged to find solutions. Then we will implement code examples in Python of basic Temporal Difference algorithms and Monte Carlo techniques. Finally, we implement an example of Q-learning in Python. I would encourage learners to experiment with the tools and methods discussed in this course. The learner is highly encouraged to experiment beyond the scope of the course. Note: This course works best for learners who are based in the North America region. We’re currently working on providing the same experience in other regions....
Filter by:

1 - 7 of 7 Reviews for Introduction to Reinforcement Learning in Python

By Jesus M Z F

Aug 25, 2020

Great course

By Gregory S B

Sep 29, 2020

Rhyme is pretty annoying to use because the UI and the UX is not very good in my opinion. It just tell you the model of RL without explaining in detail why we use that variables. But, it gives me insight of what RL models out there that I can explore more in the future, so I guess OK.

By Aaron S

Aug 29, 2020

This course would be a lot better titled "Refresher on Reinforcement Learning Techniques." The instructor seems to simply read sections of a textbook with the assumption that the viewer has the context already in their head. Many times they will reference something that has very little or no explanation. E.g., "gamma is the discount variable to discount a reward". They say this without explaining why gamma is necessary or useful, what a "discount" is or when you need to apply it.

The instruct pastes in code that he previously written and rushes through the explanation, oftentimes jumping to different sections randomly when he remembers he forgot to explain a relevant section. Moreover the "explanations" are brief and doesn't really make a clear connection as to why this code implements the mathematics of the model that he attempted to explain previously. It's clear the the instructor doesn't have a lot of teaching experience.

The Rhyme virtual environment is extremely hard to use, often times when i dock the video it will reset its settings and take up over half my screen and make it impossible to see the entire video and my virtual desktop at the same time - oftentimes I cant even see the whole video.

Using IDLE is a pain, please use a modern IDE like a IPython notebook or VS Code.

By Падалко М А

Dec 2, 2020

Just terrible project, no proper explanations of anything, waste of time and money.

By Vito M L

Oct 19, 2020

The instructor doesn't seem to properly know the topics he's talking about.

By Shaokang D

Nov 25, 2020

the instructor is not quite understanding the code

By Eitan I

Sep 30, 2020

don't worth the time or the fee