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
1,834 個評分
460 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.

NH
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:

26 - Fundamentals of Reinforcement Learning 的 50 個評論(共 455 個)

創建者 Andrei C

2019年9月27日

The course is overall well structured and concise. I am sure that the instructors could do a better job of putting more emphasis on the difficult parts of the course (such as how to actually use the Bellman Equations and how to calculate the State/Action Value functions). More examples of calculation would have made things far easier. All in all, it was a decent introduction to RL and the videos cleared some of the confusion that arised just by reading the RL handbook by Sutton & Barto.

創建者 K. S

2019年9月22日

Some of the sections seemed a bit rushed up. While the book provided a good source to clarify, I would prefer a slightly slower pace with emphasis on understanding during the video presentation. However, I have learnt significantly on reinforcement learning during the course. Thanks to the instructors who are highly accomplished, and have taken the time to create this video course.

創建者 satheeshkumar v

2019年9月12日

What ever the content taught was really really good. but still more hands-on algorithms such as Monte Carlo would have been even better. overall worth studying the course

創建者 Akshay P

2019年10月23日

Good overall. Need to work with your assignments and their submission procedure. Lectures should be more interactive than just going through slides.

創建者 Waziha K

2020年6月4日

Course instructors should improve their teaching style by writing equations in hand and explaining point-by-point. There is no need to show their faces in the video while teaching. They sounded like 'radio' throughout the course.

創建者 Ekaterina R

2020年2月13日

Not recommended

創建者 Jonathan

2020年5月1日

Very well put together course. It does a good job of walking you through concepts in a way that's direct and accessible, while not dumbing things down. I had bought the Intro to RL textbook some months back but ran into problems getting its material to 'stick', but the ideas in chapters 1-4 are much more concrete now.

Assignments were reasonably difficult, but not overwhelmingly so. Homeworks are designed to make sure you understand key concepts moreso than being vigilantly 'rigorous' for their own sake. Emphasis of the class is making sure you understand fundamental concepts moreso than hacking your way into a working prototype of something.

While the class is designed to be easily digested, the material assumes a working knowledge of programming and mathematical formalism, so people without some background knowledge you might struggle to keep pace, even if the material is well designed.

Also, like others have mentioned.......this class follows the book pretty carefully. Don't expect anything to be covered that's not in the RL textbook the course is based off of. By the end of the class the book material will be more vivid and concrete in your mind, but you will not have branched into a direction not covered within it.

創建者 Daniel S P G

2020年12月30日

The course is very good, I already had some experience with Markov chains. I found the hardest part to understand was week 3 with the Bellman equations. The course should be reinforced in this part so that everyone can understand, and it would even be to pass some of the material in this section to the second week (since it is a lot of topic).

I had to do a lot of research with other sources to be able to understand the content of week 3, since the book is not very clear material, especially on this topic. It would be very interesting if you could explain us better how to create these environments that are mentioned (eg GridWorld, Pole Car, etc) in Python in order to improve the form and intuition in the application of these concepts, this as off-topic material.

The guest talks were very beneficial to me, they give some very interesting historical and practical perspectives on the application of the concepts. Professor Warren Powell's talk was the most interesting in my opinion and he left me wondering how we could apply these concepts to real life problems.

Thanks to the team for this course.

創建者 John W

2020年9月11日

This course teaches you by having you read the textbook chapters (free pdf) followed by complementary videos that help you gain intuition. The quizzes focus on you truly understanding the material and are not easy. Quizzes plus two programming assignments help you actively learn rather than just passively reading or watching videos. I do wish the Discussion Forums kept a longer history of Q&A and had more responses from the instructors and mentors. For example, I had a question that someone else had already asked (so it wasn't an unusual question), but there was no response, and enough time had passed where the post became locked from any responses. So, I would really rate this course as 4.5 stars.

創建者 Mukund C

2020年3月7日

Phenomenal Course. Very nicely done. Wish there were more active mentor engagement, however, since the student community for this course is not as large as at the time of this writing, so not much material to search through in the discussion forums. It will be good if some of the videos are consistent with the book - e.g. the notion of "control" is not in the text, but is introduced in Week4 for DP. Also, it'd be great to have some more lectures that dig deeper into "alternate" representation of Bellman equations (we are thrown this question in the quiz, but some working professionals, like myself can be quite rusty in English<=>Notation mindset, but that's a "very" small nitpick item.

創建者 Maximiliano B

2020年1月30日

This course is excellent and it is a great introduction to reinforcement learning. I really liked that an electronic version of the book from Sutton and Barto is available for download as part of the course. However, it is fundamental to read the book in advance before watching the videos every week to have a better understanding of the concepts. Mr. and Mrs. White explain the content very well and it helped me a lot because the book is sometimes quite abstract if you are dealing with this subject for the first time. I definitely recommend this course to have a solid foundation in Reinforcement Learning and I am looking forward to start the next course of the specialization.

創建者 Everest L

2020年5月7日

I've taken a few Coursera courses on machine learning/AI, and this is by far my favorite one. I love how the course is theoretically rigorous while still providing you with hands-on practice. Note: the short lecture videos don't contain all useful details, reading the (free) recommended textbook is a wise thing to do. Sometimes the quiz questions are drawn from the textbook, with slight modifications, and you'd be glad that you've worked through them prior.

No need to fret over reading every page of the textbook either, because recommended page ranges are given and they help.

創建者 Mateo

2019年9月17日

I found the course really helpful. I have been learning RL for some time and it was hear that almost finally i can say that a lot of the concepts that were vague in my head became clearer. Also it made me look at the book of Sutton and Barto and found that it was a good experience. Maybe more examples and questions in between videos as in deeplearning.ai of Andrew NG could be good for keeping with the attention could be nice. Also maybe doing more programming exercises in between the ones we did in order to implement each step would be great. Thank you very much!!!!

創建者 Leyong L

2021年2月26日

Pros: - the time required to complete this course is reasonable and flexible

-the teaching videos explain unclarity from just reading the textbook.

-the practical examples and programming exercises help learners to relate the learned knowledge to a greater context

Cons: - some part it is not clear what do the variables of the equation meant and how it is related to real-world variables. (nevertheless, the user can find resources online to better understand the mathematics behind reinforcement learning)

創建者 Douglas D R M

2020年7月1日

I believe that, as of now, this is the most educational and informative resource available online to learn the fundamentals of RL from scratch. the instructors use Sutton’s book as reference material (which is freely available online), guide you to details that no one would know are important when studying RL alone and prepare you to venture further into the area, with a solid foundation. I definitely recommend this as a starting point for anyone who wants to dig deep into RL.

創建者 Saraj s

2019年8月28日

This is the best RL course I have ever attended. Even before starting this course I had brought the textbook (the one which course instructors also recommend) and was through the first 4 chapters. I understood most of the material but when I attended the class, everything was crystal clear. I hope instructors follow up and create the remaining courses as well. Please increase prgramming assignments in number as well. Thumbs up. Thanks for this course, very grateful.

創建者 Kaylee Z

2019年10月3日

I really like this course. This course introduces the basic mathematical background needed in RL, as well as provided algorithms and hands-on programming practices in translating algorithms into actual code, which is a well-blended material for students to learn! The quizzes are very helpful as well, which helps me understand the concepts better. All the methods discussed here are quite practical and intuitive. Thanks Martha and Adam making this course fun!

創建者 Mohamed S R I

2019年12月22日

The material in this course is of interest or me. It combines both theories and practical aspects of RL. The course follows the standard book in RL (Sutton & Barto Book).

One improvement may be needed is to add more "modern" examples and programming assignments/modules to explain the concepts. Also, it would be nice if the instructors can sometimes reflect on their own experiences with RL, rather than exactly following the book.

創建者 Tianwen M

2021年2月3日

This course provides me the fundamental principles of RL! I like the clarity of each module (because I tend to be lost in the textbook only). In addition, I really appreciate the programming assignments of this specialization which helps me gain a deeper understanding of the basic concepts. I used to be afraid of dynamic programming, but I think I am confident enough to study more complex problems using DP in the future.

創建者 Xiao Y

2020年8月19日

I have been interested in RL for a while and have watched many videos taught by other researchers, but this one provides something unique that helped me really get a deeper understanding of RL and gain confidence, such as the graded exercises, the quiz, I look forward to continuing this sequence of the RL specilization! Thank you so much for making the complex concepts accessible and make the quizzes and assignments!

創建者 Jan Z

2020年8月25日

The course was very fun and informative. I really enjoyed the presentation style with clear outlines and summaries. The explanations were useful and easy to follow. Suggestions for improvements:

1) Provide a kindle version of the book, reading on screen is very tiring for eyes.

2) I think the programming exercises could use some work from SE perspective, as some of the code is not really pythonic.

創建者 Karel V

2019年12月16日

The course is very well organised and professionally made. Although it follows the first four chapters of the Reinforcement Learning textbook, it provides a little bit different narrative and thus serves as a very nice complement to the textbook. Most importantly, interactive quizzes, programming exercises in Python and plenty of visualisations help to strengthen understanding of the concepts.

創建者 李谨杰

2020年4月25日

This course is the best course I have taken in Coursera! As a learner of RL in a non-English-speaking country, Sutton's book is too hard for me to accept a new idea very quickly. However, after watching the short videos in this course that summarize the core concepts explicitly, I can understand the contents of that book easily. Recommend for anyone who wants to study reinforcement learning!

創建者 Christian C

2019年8月4日

Exceptional course, the fundamental of RL explanations are excellent! I in particular I found it insightful the focus on thinking about examples in real-life that can be modeled as Markov Decision process. Additionally, great quizzes questions and assignments all helped in deepening my understanding of topics such as Dynamic Programing, Bellman Optimality, and Generalized Policy Iteration.

創建者 Justin S

2019年8月23日

Excellent Course! The level of difficulty is perfect. It is difficult but not impossible if you do the readings in the textbook and understand the lectures. I strongly suggest reading the book before watching the lectures. This helped my understanding significantly. The material and assignments are very interesting and informative.

Highly recommend this course to anyone interested in RL.