Chevron Left
Prediction and Control with Function Approximation に戻る

アルバータ大学(University of Alberta) による Prediction and Control with Function Approximation の受講者のレビューおよびフィードバック



In this course, you will learn how to solve problems with large, high-dimensional, and potentially infinite state spaces. You will see that estimating value functions can be cast as a supervised learning problem---function approximation---allowing you to build agents that carefully balance generalization and discrimination in order to maximize reward. We will begin this journey by investigating how our policy evaluation or prediction methods like Monte Carlo and TD can be extended to the function approximation setting. You will learn about feature construction techniques for RL, and representation learning via neural networks and backprop. We conclude this course with a deep-dive into policy gradient methods; a way to learn policies directly without learning a value function. In this course you will solve two continuous-state control tasks and investigate the benefits of policy gradient methods in a continuous-action environment. Prerequisites: This course strongly builds on the fundamentals of Courses 1 and 2, and learners should have completed these before starting this course. Learners should also be comfortable with probabilities & expectations, basic linear algebra, basic calculus, Python 3.0 (at least 1 year), and implementing algorithms from pseudocode. By the end of this course, you will be able to: -Understand how to use supervised learning approaches to approximate value functions -Understand objectives for prediction (value estimation) under function approximation -Implement TD with function approximation (state aggregation), on an environment with an infinite state space (continuous state space) -Understand fixed basis and neural network approaches to feature construction -Implement TD with neural network function approximation in a continuous state environment -Understand new difficulties in exploration when moving to function approximation -Contrast discounted problem formulations for control versus an average reward problem formulation -Implement expected Sarsa and Q-learning with function approximation on a continuous state control task -Understand objectives for directly estimating policies (policy gradient objectives) -Implement a policy gradient method (called Actor-Critic) on a discrete state environment...



Well peaced and thoughtfully explained course. Highly recommended for anyone willing to set solid grounding in Reinforcement Learning. Thank you Coursera and Univ. of Alberta for the masterclass.


Surely a level-up from the previous courses. This course adds to and extends what has been learned in courses 1 & 2 to a greater sphere of real-world problems. Great job Prof. Adam and Martha!


Prediction and Control with Function Approximation: 101 - 125 / 126 レビュー

by Narendra G


This course is important for those who not just want to learn RL for mere sake but want to dive into various topics currently in research (for that reading textbook is of most importance). This specialization would have been even better if it had included some more complex topics from the textbook. To fully comprehend all the topics, guidance from experts is necessary.

by Nicolas M


Very interesting course: I have learned many things. A translation to other languages would be great: sometimes I can't memorize everything as I would if it was in my mother tongue.

Using another paper to study ( Experiments with Reinforcement Learningin Problems with Continuous State and Action Space) was a great idea that should be done in other courses.

by Lucas O S


Great course, deserve 5 stars. It is a good complement to the book, it adds interesting visualizations to help parse the content. The only issues were in the exercises. There are technical issues with the notebook platform where it keeps disconnecting from time to time, with no warning, and you lose your unsaved work (seems like token expiration).

by 남상혁


Very good lecture! I understand a lot about function approximation such as linear approximation, neural networks, etc. However, detail of video lectures were not perfect as the textbook. If you don't want to read a lot of text and listen to the lectures, you might not understand a lot of concepts.

by Hugo V


it was great to apply what I have learned from the book, but it was hard to find my mistakes in the course 3 notebook. I also misunderstood the alphas in the course 4 notebook at first glance, their indices look like they are powers (sorry for the bad english). Besides it, great course.

by Amit J


Lecture quality could have been better. They look like practiced monologues rather than a class where a teacher is trying (hard) to explain a concept. If one has to wait for assignment to get the full grasp, it doesn't reflect too well on the instructors.

by Lik M C


The course is still good. But the assignment is not as good as course 1 and 2. In fact, the contents of the course are getting complicated and interesting as well. But the assignments are relatively simple.

by Mark P


Solid intro course. Wish we covered more using neural nets. The neural net equations used very non-standard notation. Wish the assignments were a little more creative. Too much grid world.

by Anton P


There is a lot of material covered in the course. Be aware the pace picks up considerably from the first two courses. This said, it is a worthwhile course to take.

by Vladyslav Y


I wish agents that are based on visual information (with the usage of CNN) would be included in the course. But overall that was really great!

by Sharang P


more detailed explanation of some of the assignments and how state values are got with tile coding but overall a great experience!

by Jerome b


Great course, based on the reference book about reinforcement learning. A must for anyone interested in machine learning.

by Rajesh M


I loved the course videos and programming assignments. The only suggestion would be to go a little deeper in the videos.



This was a good course but I really struggled to understand how each of the value functions translated into code.

by Muhammed A Ç


Programming exercises are not self explaining. But instructors are explaining concept in a perfect way

by Pouya E


Great overall. The content on policy gradient could be expanded, some details were delivered hastily.

by Rishabh K


The average reward and differential return needs to be explained more thoroughly

by Ramaz J


Course is great! Maybe some slides would be helpful not to forget.

by Charles X


Gets hard to understand.

by Quarup B


Content is great, but the text is super dense -- slow read for me. The lectures are much clearer, although also a bit dense / quick paced to retain the information long term (especially if one wishes to skip the reading).

by Prashant M


great course material but you need read the RL book through out the course. Also assignments are bit difficult, oops concept is mandatory.

by Justin N


Lectures are pretty good, but the programming exercises are extremely easy. All of the problems are rather contrived as well.

by Yassine B


I think It must be more deep neural networks dedicated course and not focus on coarse and tile coding!!!

by Bernard C


Course was good, but assignments were not well constructed. Problems with the unit tests were frequent.

by Lars R


Feels to be too focussed on theory and math, instead on practically applying the best techniques.