Chevron Left
返回到 Fundamentals of Reinforcement Learning

學生對 阿尔伯塔大学 提供的 Fundamentals of Reinforcement Learning 的評價和反饋

4.8
2,328 個評分
557 條評論

課程概述

Reinforcement Learning is a subfield of Machine Learning, but is also a general purpose formalism for automated decision-making and AI. This course introduces you to statistical learning techniques where an agent explicitly takes actions and interacts with the world. Understanding the importance and challenges of learning agents that make decisions is of vital importance today, with more and more companies interested in interactive agents and intelligent decision-making. This course introduces you to the fundamentals of Reinforcement Learning. When you finish this course, you will: - Formalize problems as Markov Decision Processes - Understand basic exploration methods and the exploration/exploitation tradeoff - Understand value functions, as a general-purpose tool for optimal decision-making - Know how to implement dynamic programming as an efficient solution approach to an industrial control problem This course teaches you the key concepts of Reinforcement Learning, underlying classic and modern algorithms in RL. After completing this course, you will be able to start using RL for real problems, where you have or can specify the MDP. This is the first course of the Reinforcement Learning Specialization....

熱門審閱

AT

2020年7月6日

An excellent introduction to Reinforcement Learning, accompanied by a well-organized & informative handbook. I definitely recommend this course to have a strong foundation in Reinforcement Learning.

HT

2020年4月7日

This course is one of the best I've learned so far in coursera. The explanations are clear and concise enough. It took a while for me to understand Bellman equation but when I did, it felt amazing!

篩選依據:

526 - Fundamentals of Reinforcement Learning 的 550 個評論(共 562 個)

創建者 Eli K

2021年10月31日

Programming exercises teach the material a lot better than quizzes

創建者 Sriram S

2020年4月17日

The course was cool but needed some more programming assignments.

創建者 Francisco R

2020年6月15日

Excellent in terms of learning the foundations of RL.

創建者 袁之日

2021年3月29日

There could be more coding examples for each module.

創建者 Jeroen v H

2019年10月17日

Quite theoretical. But a good base of the concepts.

創建者 Husam D

2019年11月4日

I wished there were more coding assignments

創建者 Shahram E

2020年6月25日

c

o

u

l

d

b

e

w

i

t

h

m

o

r

e

e

x

a

m

p

l

e

a

n

d

t

e

a

c

h

b

y

c

o

d

i

n

g

創建者 Matin S

2022年1月13日

it was a bit hard in code assignments

創建者 Mark R

2019年10月26日

Interesting course.

創建者 Arnaud 3

2021年10月10日

good course

創建者 Abhishek U

2022年1月21日

Great

創建者 배병선

2019年10月31日

Good!

創建者 Arpan M

2020年10月17日

good

創建者 Austin H

2022年3月19日

I found this course difficult to get through, even tedious towards the end; this is a fundamentals course after all so it being heavily theoretical was to be expected.

I found the practical assessments challenging and very good for developing the understanding of what had been taught; however one practical in the first week and one in the fourth week was too few. I was longing for the final assignment!

It remains to be seen how relevent this is to the upcoming modules (I do feel that I have a good grounding and understanding of the underlying process so maybe it was a necessary slog). I hope that they are more practical!

Very small observation: the use of bespoke Python packages with the online notebooks was also a bit frustrating. I like to be able to work off line (e.g. in Anaconda) and I also wanted to try and work out some of the challenges in R but without access to the bespoke packages it would have been too involved. I understand that you have a lot of students though and online notebooks are easier to manage.

創建者 Youval D

2020年1月21日

Good examples can simplify things greatly. there where several places where an extra step would add value. Some lessons, such as the problem with the trucks could go a little deeper. Assignment grading system is buggy. I spend hours (that I do not have) because I used "transition" as a variable. After I figured this out, I was no longer able to know if other error is due to some other things the Notebook does not like or if there are actual errors. I also posted some questions but never got any response to any of them.

創建者 Chandan R S

2020年5月9日

Not much satisfied with the course structure...

To successfully understand and complete this course, you constantly need to refer the reference book.

Most of the students are referring to online courses so that they can learn more efficiently than reading,

any casual book reader can easily complete this course but for the person who like to learn from videos rather than book reading (like me), it was not so great experience.

創建者 Rafael C P

2020年5月12日

The content is there and it is good, but teachers lack good teaching skills and lessons feel rushed (Ng lectures come to mind as positive examples of good practices). Also, lessons aren't self-contained, as you need to read the book if you want to get good grades on the tests. I was looking for a smoother experience than the book, not to be told to read the book, which I can do without a course.

創建者 tom

2020年12月16日

I would have learned more if the course had a coding assignment each week, or at least example code available for similar problems. I had a good theoretical understanding of everything we needed to do but very poor practical understanding.

The course did serve as a good introduction to the theory of reinforcement learning, and certainly acts as a good starting point.

創建者 Vaddadi S R

2021年3月10日

The programming exercises are quite tough and difficult to code on our own. Concepts were explained nicely, however, lacks examples. Working out examples would have given an even better insight. Another video that could have proven useful is how to convert a real-world problem into an MDP.

創建者 Thomas T

2022年1月26日

Course is rather poorly structured. Some videos explain concepts better than others but come later in the courses. There's not enough of a summary of terms, and seems to follow the suggested book almost word for word. The course should use the book as supplementary not complimentary.

創建者 Saeid G

2019年12月10日

The good thing about this course is that it is based on the bible of reinforcement learning and it is thoughts by the experts in the field. However, the pace of the teaching is extremely fast and it is quite hard to keep with the pace even for someone with some background in the RL.

創建者 Iuri P B

2020年7月3日

It needs more explanation about the fundamentals, examples and sections that demonstrate how each, for instance, Policy Iteration and Value Iteration differ. Despite that, the course is really good and I would recommend for a friend.

創建者 Amr M

2021年3月14日

The material needs to be easier and more intuitive. Last assignment shall have some additional steps to help the student to solve it. and also to involve him more

創建者 Soran G

2019年12月9日

The size of different variables has not been clearly spelled out so this makes the concept confusing and requires so much time to figure them out.