返回到 Fundamentals of Reinforcement Learning

星

2,222 個評分

•

541 條評論

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....

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：

創建者 Nikhil S

•2020年11月22日

Great material! The course was very well taught and at an appropriate pace. I do think that the teaching style was a bit too formal, however. Also, the entire course, lectures, and order are centered around the book which is easy enough to understand on its own. It might be useful to discuss some practical tips and methods instead of only the book theory. Learned a lot anyway. Thank you!

創建者 Ananthapadmanaban, J

•2020年5月23日

Reading all weeks' suggested sections from the book before going through the videos would make it easy to understand the concepts. I actually read after watching half the videos, but it makes more sense to read before the videos. The assignments are decent. Policy evaluation, policy iteration and policy improvement are the concepts the course is trying to explain.

創建者 Satish C R

•2020年10月6日

I have definitely learned basics of reinforcement learning by taking the course. In my opinion, to really absorb the material, one needs to read the provided textbook carefully and do the exercises. I suggest doing the some of the textbook programming problems as well to really learn the material. The videos only provide an overview.

創建者 Rishi R

•2020年8月3日

An amazing course with great insights that drive a new learner in this field want to know more. The only slight drawback I felt was in missing details in implementing the algorithm, which of course the assignments took care of. Yet a good elucidation of the algorithms step-by-step will give a better understanding.

創建者 Arun R

•2020年2月12日

Great class and I learned a lot - docking one star because the final programming assignment didn't give a comprehensive enough checker inside the Notebook, so I had to keep submitting and look to discussions for help in solving (for really a minor issue that it looks like many students faced on an edge test case).

創建者 J B

•2020年6月15日

A very well constructed course with two excellent lecturers leading it. A lovely introduction to RL although some may prefer a more mathematical treatment (in which case you need to find a longer course). No tutorial support during the course though so you need to be prepared to sort out your own problems.

創建者 Sebastian T

•2020年2月22日

Slightly too theoretical but clarified couple loose ideas and enabled me to work with python a bit. although a t the beginning of the course they speak that it is not about python, we actually get a chance using it although indeed we are not getting nice python code examples in course materials.

創建者 Russel C

•2020年2月15日

Really good introduction to Reinforcement Learning foundations. The lectures were great, and helped translate the theory from the RL book. I would like there to be a few more detailed walk-thru of the update algorithms in week 4, but I was able to work through the programming assignments okay.

創建者 Shashidhara K

•2019年11月13日

I really sorry for giving 4 star, my only reason for giving 4 star is so you can read this review. Please include some exercise on calculating the equations by hand, with solutions(this is the only reason for 4 star).

Thank you for the course

Course deserves 5 stars.(pardon my 4 stars, sorry)

創建者 bob n

•2020年12月22日

For me, math a bit harder and more opaque than other ML courses I've taken. Even though only a few lines, final programming assignment one of more challenging ones in taking book equations to python implementation. Explanations pretty clear in videos.

創建者 Lucas L

•2021年4月8日

Great course with interesting material and good examples. The only reason for rating 4 and not 5 is because I feel that programming assignments are a little too easy. Maybe they could benefit from letting the student implement more parts.

創建者 Dror L

•2020年7月31日

Clear and pleasant recorded presentations. Very good and precise reading materials. Time estimate for reading materials are super optimistic. Guest lectures are at best inspiring. No real value. They are unfocused and all over the place.

創建者 Ed J

•2020年4月25日

I think the course was well put together and the labs were clear. My only real complaint is that the book and tests spent a lot of time proving and manipulating equations. I am mostly interested in using the formulas and programming.

創建者 Aresh B

•2021年1月13日

The coding assignments are a bit confusing. If you expand on coding assignment and probably provide a more step by step instruction as how the functions are being defined, or how the environments are created it would be way better.

創建者 Alper A

•2020年3月29日

Course is fine, but there could be more coding practices then the theoretical part. There are two coding assignments which are hard to do only with the course. The course context could be extended to include more coding practices.

創建者 Ayse E G

•2019年9月28日

The course is a very good introduction to RL but the concepts are handled a little too abstractly. However this provides an excellent fundamental for the rest of the courses. I would have liked more programming exercises.

創建者 Mauri K

•2020年11月23日

A very useful and also rather compact course. I can recommend to anyone interested in the subject matter. I did expect a little bit more hands-on action (ie. more concrete, yet still simple examples in the coding side).

創建者 Aravind M

•2020年10月26日

A really good introductory course to RL. The instructors have structured the course in the same manner as in the specified textbook (which is also great), so it's easy to follow them both at the same time.

創建者 Aaron H

•2019年9月10日

Great material, and awesome coding exercises. Some additional information or context around a few of the problems would have been great, but nonetheless the struggle allowed me to grow in my knowledge!

創建者 Aboozar R

•2020年10月28日

The video lectures were very short and just a repetition of the book itself. After we studied the book, the lectures didn't have anything new for us. They should have been different and more hands-on.

創建者 Aidan M

•2020年8月24日

Don't think it would be unreasonable to have more demanding coding assignments where all functions are made from scratch (though the function names and some comments might be provided as an outline.

創建者 Ulf Ä

•2021年1月3日

The book is essential reading. It took me longer than the estimates to do the reading and the programming assignments. I would have liked more gridworld examples to get a faster hang of it.

創建者 Christian J R F

•2020年4月1日

Great course, I think theory is really well explained and book is great, but including more practice exercises is needed for this course to strengthen the learning of concepts.

創建者 Narendra G

•2020年6月5日

The course is well developed, reading the reference book is the most important thing that you will do while taking this course. The delivery of both instructors seems robotic.

創建者 Nils S

•2020年10月29日

Very good an enjoyable course. It seemed like the explanations dwelled on the easier parts and skipped the parts that I would like to have seen in concrete numbers.