返回到 Fundamentals of Reinforcement Learning

星

2,215 个评分

•

540 条评论

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

Jul 6, 2020

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

Apr 7, 2020

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!

筛选依据：

创建者 Stelios S

•May 11, 2020

This is the BEST course I've taken from Coursera, period. The level of explanation, the usage of mathematically precise terminology, the walking through of the algorithms, the summaries were all top-notch. This course will be my reference when I forget something in the future. I can't thank the creators enough.

创建者 Ali N

•Apr 1, 2020

It was a very good course, I had read Sutton's book first. But I must say that after completing this course, I learned the concepts of the book well. Although the exercises were a bit tough, they covered the topics well and increased learning at a faster rate.

For anyone interested, I recommend this course.

创建者 Alejandro A Z

•Jul 20, 2020

It was really cool! Although I think there should be a forum where students could ask and answer questions. I got stuck for a silly mistake before delivering the last python notebook and could have used some help.

Still, I learnt an incredible amount of concepts that I didn't imagine were so important!

创建者 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.

创建者 Nicolas T

•Apr 26, 2020

Great course! The idea of suggesting reading before the videos gives a huge boost to the depth of the class. This, with the "not-too-straightforward-quizzes", and the assignments, makes it a real deep class, from which I'll probably learn and retain more than most online courses. Good job!

创建者 Anton P

•Dec 14, 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.

创建者 Dante K

•Dec 28, 2020

Teachers were very clear and so was the book. The only thing I feel could be improved is adding some coding exercises on Week 2 and 3 (there's only one at Week 1 and one at Week 4, with a Peer Reviewed assignment on Week 2 which was fun, but didn't feel as useful as coding exercises)

创建者 Sandesh J

•Jun 1, 2020

One of the best available courses on Reinforcement Learning. The instructors have explained all the underlying topics elegantly. Good blend of theory and numerical in assignments and programming problems. Moreover, the assignments have covered different perspectives on these topics.

创建者 Sara S

•Dec 28, 2020

Excellent Course. Although it was only 4 weeks course, I learned more than reading an entirely dynamic programming book which might take more than 3 months for me. It was a well-presented course and I suggest this course to the ones that want to learn about Dynamic programming

创建者 Giulio C

•Jun 25, 2020

Amazing course!

The book, on which this course is based, is a bible for reinforcement learning. Anyway, it could be hard to understand. The lectures of the course eliminate all doubts and consolidate all the concepts, ensuring a complete comprehension on the subject.

Thank you!

创建者 Bae,Bongsung

•Apr 20, 2020

Great starting point for learning Reinforcement Learning. Anyone who is interested in the state-of-the-art RL techniques should take this course first, or they will have hard time getting through the more applied and sophisticated concepts found in the tech blogs or papers.

创建者 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.

创建者 Juan C E

•Feb 9, 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!!!

创建者 Rohit P

•Jul 25, 2020

Some supplementary video recommendations and a little more interactive help with the Python assignments would make it more fun. Had to struggle with the programming assignments a little bit. More hands on assignments will help drive home the concepts better.

创建者 Tolga K

•Oct 15, 2020

Great course, great notebooks and great instructors, but nevertheless the reading parts of the course is most important part I think. Because if you do your reading well and really understand the material then course is just repeating over what you learn.

创建者 Yover M C C

•Mar 1, 2020

Excelente curso, aprendí los conceptos de aprendizaje por refuerzo con gran base teórica, el material del curso es muy bueno y la calidad de las lecturas es de excelente nivel. Muy recomendado, ahora a aprender más y a desarrollar sistemas inteligentes :).

创建者 Le Q A

•Aug 2, 2020

Excellent introduction. The reading materials are good, the videos make the ideas even clearer and the exercises help us get a taste of how the theory could be applied. I would recommend this course to anyone wanting to start on Reinforcement Learning.

创建者 Evgeny S

•Apr 18, 2020

I enjoyed the course. I would have preferred a bit more in-depth look at the algorithms and technical details, but, on the other hand, it was also interesting to go and figure out these contraction mapping arguments on your own. Overall, very good.

创建者 Ayan S

•Mar 18, 2021

The course videos are exceptionally brilliant. It was my first course on reinforcement learning and the instructors did a great job in making this topic look super easy and intuitive. Looking forward to the next courses of the same specialization.

创建者 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

创建者 Dan N

•Oct 22, 2021

Very good integration with the RL Book and step by step video presentations. Coding assignments well structured, however I would have liked to have more such assignments. All in all, very well though and structured course in RL fundamentals.

创建者 Manuel

•Jul 22, 2020

The most professionally presented course I have done on Coursera! Instructors explain well, the provided literature is on point and the assignments had a good mix of being doable and challenging. Probably the best course I have taken so far.

创建者 Stefan K

•Dec 4, 2020

The course covers the fundamentals of reinforcement-learning and also deals with complex mathematic equations. However the math is very good explained in the videos and the 2 programming exercises help a lot for understanding this topic.

创建者 Steven W

•May 11, 2021

Solid class covering the basics of tabular Reinforcement Learning.

They follow the Sutton and Barto book pretty closely, so they start with some dummy examples to demonstrate things. The real interesting stuff isn't until a later course.

创建者 Damian K

•Sep 1, 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.