Chevron Left
Voltar para Practical Reinforcement Learning

Comentários e feedback de alunos de Practical Reinforcement Learning da instituição Universidade HSE

4.2
estrelas
448 classificações
117 avaliações

Sobre o curso

Welcome to the Reinforcement Learning online course. Here you will find out about: - foundations of RL methods: value/policy iteration, q-learning, policy gradient, etc. --- with math & batteries included - using deep neural networks for RL tasks --- also known as "the hype train" - state of the art RL algorithms --- and how to apply duct tape to them for practical problems. - and, of course, teaching your neural network to play games --- because that's what everyone thinks RL is about. We'll also use it for seq2seq and contextual bandits. Jump in. It's gonna be fun! Do you have technical problems? Write to us: coursera@hse.ru....

Melhores avaliações

MS
11 de Jun de 2021

this is by far an AMAZING in-depth course! i enjoyed every second of it. It's challenging in a way that makes you improve. TOTALLY RECOMMEND IT. Great work guys 👏 well done and thanks for the effort!

AK
27 de Mai de 2019

This is one of the Best Course available on Reinforcement Learning. I have gone through various study material but the depth and practical knowledge given in the course is awesome.

Filtrar por:

101 — 118 de 118 Avaliações para o Practical Reinforcement Learning

por Emilio P

11 de Ago de 2019

Wonderful course. Just would need a little bit more work on the subtitles.

por Anton P

30 de Jun de 2018

It still a beta:(

por Philippe M

11 de Mai de 2020

Notebooks are very useful to learn the theory and I certainly learned a lot throughout this course. However, codes in homework often lack of clarity and sometime includes errors and not enough assert checks. The audio is also hard to and understand, the slides are often poor, missing keywords, recaps, organization, sometimes you have 4 dense slides per lessons. Would be great to have better slides as a support of the speech. The questions during videos are really useful. The teaching staff is really reactive and many issues, difficulties have already been solved by the community, which helps a lot for autonomy. So thank you, it was really really useful, but it could have been better and cleaner !

por David D

25 de Abr de 2021

The content and structure of the course are great. However, its title is misleading, for in the whole course there only one "practical" assignment (translating He to En), and all other assignments were about Atari games or toy problems. This leads to disappointment, because the presentation of the course creates expectation of many real-world applications of RL, and they are not covered by the course.

por Kristoffer M

10 de Set de 2018

The teachings are actually quite good, and the problem sets are fine, but there are so many bugs in the submission methods that you spend halv of your coding time trying to debug the submit methods. Frustrating. If they fix the course, this course will be highly recommended.

por Xiaoahe X

20 de Fev de 2019

The course is well organized. Reference and extra learning items is helpful to enhance the knowledge.

BUT! There are so many small bugs in the assignments that it really takes time to fix and make the course hard to get passed.

por Helmut G

22 de Ago de 2018

Sometimes it is hard to understand/follow the instructors. And the assignments (especially the grader) are bit too much beta, which causes a lot of extra effort.

por Felix A

18 de Mar de 2019

The course itself is great, but the assignments are a bit chaotic (so make sure to bring a lot of patience and willingness to bugfix)

por Ishan

9 de Jul de 2020

Lectures are mathematical and theoretical.

Assignments are practical. NO EXPLANATION OF WHAT ASSIGNMENTS IN CLASS

por Dai T

29 de Jul de 2018

Lots of theory and definition should be illustrate in detail on ppt.

por Sylvain D

3 de Dez de 2019

Good

por Anders A

13 de Jun de 2018

The collection of curriculum was great together with links to external resources. However, there was several weaknesses with the course. First, several of the assignments had problems with submitting the code, which required some extra coding to be able to submit assignment. Event with multiple weeks with many students reporting the problem, nothing was corrected. Second, the lectures were weak. I knew something about Q-learning from before, but after the lecture I was more confused than when I started. The topics I were not familiar from before the course,I ended up searching online or using the resources linked to instead of the lectures. The question exercises felt arbitrary and not helpful at all. The programming exercises were not well explained. I were able to finish them, but to much unnecessary annoyance.

por Maxim B

26 de Jul de 2018

Don't let Alexander Panin read lectures. He is an awful speaker: always in a hurry, uses so many redundant words in his speech. He "killed" so much interesting material in this course. I truly believe he could write cool lecture notes and handouts (currently the course lacks it). Alexander, please, write materials, don't read lectures.

por Raghu R

25 de Mar de 2020

Course is good. But too many grader issues. Accent is tough to understand sometimes. The concept is not built layer wise..Instead they dump it as a heap with tough jargon which had to broken down to be understood slowly by pausing..

por Arun A

23 de Fev de 2020

Instructors are difficult to understand. Assignment directions are not clear

por Amir N

8 de Set de 2021

Awful accent of the instructure! His accent is not comprehensible by any means. I even didn't understand what he aimed on the first week. He was talking about something like integration and deravative for no reason and you could imagine all of the equations in your mind instead of him writing them on the board. Absolutely useless course. Due to a bug in Coursera.com, I can't cancel my subscription to this course. Definitely do not recommend it.

por Antony L

12 de Mar de 2019

Course not ready and has installation prerequisites. Seems to use a libraries (Docker, Env).

I waste too much of my time trying to install libraries and dependencies for online courses, most of which become obsolete within a year or two.

Additionally, the logic embedded within the library is often the thing I want to learn, and abstracting it only teaches me about the bugs and shortcomings of that library.

por Md. S I

15 de Jan de 2022

E​nglish pronounciation is difficult to understand.