Fundamentals of Reinforcement Learning に戻る

4.8

星

652件の評価

•

167件のレビュー

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....

Nov 10, 2019

I understood all the necessary concepts of RL. I've been working on RL for some time now, but thanks to this course, now I have more basic knowledge about RL and can't wait to watch other courses

Sep 07, 2019

Concepts are bit hard, but it is nice if you undersand it well, espically the bellman and dynamic programming.\n\nSometimes, visualizing the problem is hard, so need to thoroghly get prepared.

フィルター：

by Mateo

•Sep 17, 2019

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!!!!

by Saraj s

•Aug 29, 2019

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.

by Kaylee Z

•Oct 03, 2019

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!

by Mohamed S R I

•Dec 22, 2019

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.

by Karel V

•Dec 16, 2019

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.

by Christian C C

•Aug 04, 2019

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.

by Justin S

•Aug 23, 2019

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.

by David R

•Dec 03, 2019

I really liked this course. I think it was challenging and high quality. I don't understand complaints about it following the book - I found the videos, quizzes and exercises insightful and thought provoking. And besides courses are meant to follow some material and not re-invent the wheel. Am really excited for the rest of the specialization.

by Nicolas

•Nov 20, 2019

The course was great. Very clearly explained, with meaningful examples and backup material, such as the recommended book.

My only comment will be on the case study given on the final programming assignment. The parking scenario was not very intuitive or clear for me. It took me quite a bit to understand what it was we were trying to optimize.

by LUIS M G M

•Oct 25, 2019

I started to read Sutton & Barto book this summer, and although I find it fantastic, some concepts were not 100% clear to me. This course has changed it dramatically. Now every concept is clear to me. This book is like reading a book with the support of very good explanations.

Let's go for the 2nd course in the specialitation!!!

by Иванов К С

•Aug 29, 2019

It's difficult to estimate this course because it's based on the book. I mean, 90% of materials i've seen on videos were on the book. That's very unusual, but effective. However, i've learned necessary information and python tasks were useful and interesting. I'll take the next course and will see.

by Anton P

•Dec 15, 2019

It is a very well laid out and taught course. The instructors make the material accessible with a bit of a mathematics background, or a willingness to learn. I will be taking every machine learning course I can from AMII and the UofA if the rest of the courses are of the same quality.

by Majd W

•Oct 24, 2019

The thing that makes this course outstand among other Coursera courses is that it is based on a book. That gives you more information if you need it.

One problem that I guess will be solved in the future is that there is a bug in the Programming Assignment submission code.

by Juan C E

•Feb 09, 2020

Excellent course. Excellent teachers. I love the introduction sections, in which you're presented what you'll learn in each video, and the summary section. The animated slides are also very professional. Very thorough coverage of the RL book. Congratulations!!!

by Leelamohan

•Feb 16, 2020

I had learned a clear understanding of terminology and the formulas of value function, action-value function, optimal value function, Bellman's equation, policy evaluation and iteration. It's a must go through course for Reinforcement Learning

by Damian K

•Sep 01, 2019

Slow means smooth. Smooth means fast. This course introduces you efficiently into the world of RL. And this is what you want. Everything is perfectly to the point. All exercise are here to boost your understanding. Highly recommended.

by Naveen M N S

•Sep 09, 2019

The pattern of this course is amazing. Each video is short and has a specific objective that's clearly stated. This approach to teaching made tough topics look easy. Assignments and quizzes were doable. Amazing experience overall!

by VBz

•Oct 22, 2019

Short videos, with list of objectives at the beginning and recap and the end, and clear explanations in between. In my opinion, all teachers should watch these videos to get an example on how good courses are done.

by Shahriyar R

•Sep 22, 2019

Extremely useful course. Especially the format is very effective. First read the book, then listen the extra explanations and write Python code. Concepts are really clear for me now. Thanks for such amazing work.

by Gökhan A

•Oct 22, 2019

This course is very benificial for the people who want to attempt to the area of reinforcement learning. People should regularly follow the book in parallel to video lectures to benefit from this course.

by Kaustubh S

•Sep 02, 2019

All the concepts were well explained and this course was perhaps the best I have found for RL.

Great efforts have been put into making the course and It goes well in line with the suggested textbook.

by Shi Y

•Oct 04, 2019

许多次尝试看UCL或者Sutton的课都中途放弃，太难了。而这个课程让我很轻松的入门且了解了最基本的东西。这个课程最不同的在于，学习时要配合上Sutton的书，课程和书互为补充，有些课程没有讲清楚的地方书中有很多解释，而书中生涩难懂的地方课程又有很形象详细的解释。体验极佳。特别感谢课程助教即使的回复。哪怕是书中的句子的问题助教都给出很详细的解释，真的很久没在Coursera上过这么棒的课了。

by Zhonghua Q

•Sep 14, 2019

The course is well designed. It contains the essential material of RL and relates closely with the RL Bible textbook. And the programming assignment is also benifical to understanding the basics.

by Akash B

•Sep 07, 2019

Concepts are bit hard, but it is nice if you undersand it well, espically the bellman and dynamic programming.

Sometimes, visualizing the problem is hard, so need to thoroghly get prepared.

by Herman C

•Feb 19, 2020

Excellent and well done course on some of the basics of RL. Good mix of lectures, reading, quizzes and programming assignments. Also a good balance between pure theory and examples.