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!
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.
por Lars J I•
The reading material was very weak and scattered. Some of the blog posts were nice but in general it's not very helpful to link a bunch of publications and a couple full-length books. Instead, It would be nice to have a small document that goes through the material in written form (if even just a summary).
The assignments were not very good and lacked depth. Often times I found myself implementing some formula/algorithm without knowing how it works or why. As such, it was easy to finish the assignments without learning anything. I would rather have two in-depth assignment (maybe an implementation from scratch with guidelines) than 6 or 7 shallow ones. The problem with the shallow ones is that there's no incentive to take the time and understand the functions that are already pre-coded. This makes it hard to follow whats going on "under the hood". You can, of course, still take the time to do this, but I feel like a true understanding of everything that goes on in all the algorithms in all the assignments would take far too long.
There was a general lack of theoretical material regarding the covered methods and algorithms. Why do they work?
por harsh k c•
I have completed the course. Honestly, I did not find the course super helpful because
1. Even though the lectures are in English, it is very hard to both understand the concepts and their Russian accent at the same time.
2. Not enough emphasis is given on the mathematics part. So if you want to build intuition on the concepts this course is not for you.
3. The coding assignment are like fill in the blank type questions. But more importantly it has a learning cure such that it tries to make you run without teaching you to walk properly. So the "practical" word in the course title is not justified.
4. Most importantly, there are big concept holes in the lectures. And most of the times the instructor only reads the slides just opposite to the Andrew Ng's course on Machine Learning.
por Hany A•
The course gives a good intro to reniforcement learning. I liked the fact the assignments here are shorter compared to other coursers. However, the quality of preparation of the material is very low. In many cases there are problems with the code and you cannot submit from coursera. I had to download the docker container locally and fix the bugs in order to submit. Quizes are not very nicely prepared and mathematical notation not very clear. I think I struggled a lot to get some of the quizes finished as the accepted score is quite high and some questions require multiple answers and you have to get them all right in order to get a score. I think the authors need to spend more time refining the quizes as well as the assignments
por Sandeep K C•
One of the speakers speaks too fast
Many things are not fully covered and have to refer to outside the course
Most importantly the exercises have bugs or do not have enough guidance
por Ashish J•
Horrible graders starting from week 3. A lot of time wasted in fixing grader issues which is course provider's primary job. This is a paid course for goodness sake. No proper communication by course's staff/mentors even in the discussion forums.
por Esmaeil N•
It is one of the worst courses I have ever seen... The concept are not well organized... there is too much in each presentation... the presentation itself is horrible... all in all, it was really difficult to bear the course until the end....
por Florian P•
No structure in the lecutre, no lecture notes. The teachers are very hard to understand. The tests and programming assignments are bad explained and are different from what is taught in the lecture. Not worth the money.
por Robert E•
Instructor talks to fast and is hard to understand. Materials are full of bugs (which they admit).
por Michel C•
Submission python code is very buggy. Instructors are hard to understand.
por Hermes M G•
The course is presented as advanced in an Specialization named also advanced. So, if you are not already an specialist, you will face some challenges.
In the overall, the course shows clearly which is the subject comprehension degree that should be attained for a person to consider himself an specialist. This is already a remarkable achievement.
Also, the excercises and presentations logic and contents is high quality, and they - as a bonus- conduct the learner towards other interesting sources.
This is a great introduction to reinforcement learning.I faced some problems in submitting assignments but the course content and the extra materials are really good.I think it is to RL what Andrew Ng's Course is to ML . You will implement algorithms like cross entropy method to DQNs and A3C .Assignments uses Open AI Gym so you can get some good practical results .Overall I loved this course and would like to recommend to any one who is getting started in Reinforcement Learning.
por Jose S•
This is a great course. There are some technical issues with the assignments but we knew this going in since the class is still in Beta. I learned a lot working through sections of the honors track. I recommend you download the assignments, install all python requirements and work locally. It would be great if they had a TA for this class, fortunately people in the forums were super helpful.
por P C•
Brilliant course, from top to bottom! An amazing introduction to the state of the art in deep reinforcement learning, with plenty of practical exercises. There are enough 'bonus' materials to keep someone busy for an entire graduate degree. I will refer back to the materials in this course, over the years, and use them as an inspiration for my future projects. Excellent job guys!
por Владимир М•
This course provides a very good foundation for understanding modern reinforcement learning algorithms and very recent articles. Although several homework is in beta, the course covers extensive reinforcement learning algorithms. However, in order to understand many topics, I had to search for alternative sources and articles on the Internet.
por RAM H•
This is one of the best courses I have taken on Coursera, The course is very rich in content and methodically developed. Both lectures have done a wonderful job in delivering lecture with full energy and make difficult concepts graspable. Both programming assignments and quizzes are well thought out. My sincere appreciation and thanks.
por Marcin G•
Great practical assignments based on gym environment (from Open AI). Quizzes on the other hand tend to be very challenging and therefore might be a bit exhausting. Practical assignments are well designed and explanatory. I am convinced, that programming practices make it the best course on reinforcement learning currently available.
por Samuel Y•
By far, this course has the most guided assignments with grader and tutor forum feedbacks in the specialization. Most of the work could be finished in coursera notebook, except several honor homework needs GPU to speed up. Yet, there're a bunch of mistakes to be fixed before submitting. But still a good course to learn a lot from!
por Anubhav K•
Loved the course, both the lecturers, especially Alexander Panin's enthusiasm kept me going and motivated for the course. Though there are some issues with the assignments, overall they were a great learning experience solving them. I'll recommend this course to everyone who wants to dabble into reinforcement learning.
por Dmitry I•
A great overview of the most common and significant reinforcement learning techniques, backed with some theory and a multitude of references.
Practical assignments are well calibrated - the bare minimum to pass is quite easy to achieve, and more material is available for the more dedicated students.
por Milos V•
This is my fourth AML course, and for now I would say it is the best one. It connects lectures and practice in the best way. On the other hand, there are mistakes all around, as it is beta-version. In my opinion, it is not fair to put the beta-version course into paid specialization.
por Debasis U•
I loved this course, many things I have revisit to get a complete and thorough understanding, there is so much happening and so much to learn, and this course certainly showed me the possibilities. Thanks to the instructors and Coursera for this course
por Florian A•
Very insightful ! I appreciated the balance between concepts & theory explanations in videos and practical applications in notebooks. If you're interested in Reinforcement Learning, especially with coding sessions, this is course is a must !
por Anmol g•
The content was tough but the efforts were appreciable even if there were some hiccups along the way. The best part of the course was the plethora of information you get, don't forget to check out the references at the end of notebooks ;)
por Zoltan S•
This is a challenging course. The material and the lectures are excellent. (There are a few minorproblems discussed in the forums where you might need a little patience and determination, but it is well worth it). I highly recommend it!
por akshay b•
Although still in its beta version this course is a comprehensive introduction to reinforcement learning.It doeshas some bugs in submission and in assignment code which I hope will be dealt with in future versions