Prediction and Control with Function Approximation に戻る

4.8

星

424件の評価

•

75件のレビュー

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...

Jun 25, 2020

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!

Jun 01, 2020

I had been reading the book of Reinforcement Learning An Introduction by myself. This class helped me to finish the study with a great learning environment. Thank you, Martha and Adam!

フィルター：

by George G

•Feb 29, 2020

Fantastic course! Despite the challenging content, this course actually is taught at least at the same level as the ones by Andrew Ng, Daphne Koller, and Geoffrey Hinton. Congratulations Martha and Adam! You are awesome and are my heroes! Thanks a lot! George

by Mukund C

•Mar 27, 2020

Excellent Course and Lectures. Loved it!! So important to read the chapters in the book ahead of time. Book is also excellent!! I liked the way the instructors explained the equations and broke them down. Nicely done!! I wish some more of the questions in the quiz reflected the data structures we use in the programming exercise, which will be super-helpful to reinforce the concepts when we do the programming exercises. In other words, an intermediate step of a worked example between the Pseudo-Code Algorithm in the Texbook/Lectures and the Programming Exercise. For example, more of the Feature_Vector -> Action_Value Calculation - even if we have to do some matrix manipulation by hand, that'd be wonderful. One of the quizzes has something like that (but more simplified) - which was perfect.

by Navid H

•Oct 16, 2019

The material is very good. But this course needs better instructors/ method of teaching. The book is also written in an unnecessarily technical way filled with jargon. explanations are not clear, simple stuff is presented in a very complicated manner for no obvious way.

by Maxim V

•Jan 23, 2020

Good content, but there was a highly unpleasant surprise in the programming assignments, namely this: "Retakes: You can attempt this assignment 5 times every 4 months." First of all, this is a highly unusual and therefore unexpected requirement on Coursera. Also, considering how buggy graders are and that some assignments require submitting results separately from the notebook, this is a really high risk of having to wait 4 months for another chance.

by Maximiliano B

•Mar 31, 2020

The third course of the specialization is excellent and it provides a solid foundation on problems with arbitrarily large state spaces that rely on approximate solution methods. The lectures are very well explained. It’s strongly recommended to read each book chapter in advance before watching the lectures to be able to better understand the concepts and be able to answer the quizzes. The content in this course is quite abstract and it is heavily dependent on statistics and calculus. It was very nice to integrate reinforcement learning with neural networks as part of one of the assignments as well as to implement the swing-up pendulum. I am looking forward to begin the capstone project.

by David R

•Dec 31, 2019

Excellent course. The videos, quizzes, and especially the exercises add a lot of extra value to the text book (which is available for free - Sutton and Burto, 2nd edition). Of course it is not perfect - the videos are sometimes a bit dry, the NN part was brushed over too quickly for a beginner (luckily I had taken some courses about deep learning, so I was ok - but if you don't know the basics of NN, week 2 might be quite challenging for you). Other than that the biggest disadvantage is that the course forums are still quite empty - and so if you get stuck you can be on your own... But you shouldn't get stuck, and I guess this will improve over time.

by Mark J

•Oct 23, 2019

This, the third in an exceptionally well-paced series of four courses on Reinforcement Learning, extends the scope of the subject to include parameterized functions (i.e., neural networks). The section on tiling methods is especially interesting. The course is taught under the auspices of professors who, quite literally, wrote the book on reinforcement learning, and includes several video lectures by leading practitioners and theorists in the field. The final programming assignment, in particular, made me feel like I did when I wrote my first computer program that actually did what it was supposed to way back when -- delight and amazement.

by Julien T

•Nov 12, 2019

Great course and specialization. The teachers are great, the material well presented and balanced. I strongly recommend this course to anyone interested in the field of Reinforcement Learning. For maximum chance of success I suggest following all 3 courses in succession and investing the necessary amount of time to read the textbook chapters as specified at the beginning of each week.

Looking forward to completing the capstone project now!

by Gordon L W C

•Mar 23, 2020

The course is very comprehensive on the content. But I think the difficulty of this course is in some sense too high for most people who don't have a background in engineering degree due to the extensive use of advanced mathematics. I think it might be a better idea if you are focusing on a few critical algorithms that trying to cover too much algorithms which is quite overwhelming

by Walter O A

•Dec 09, 2019

An almost overwhelming amount of material, however we managed to navigate through the thicket. The labs were well maintained and provided robust tests so that one could have a high degree of confidence in the solution before submitting to the grader. I really appreciate this. I would recommend this course to anybody wanting a serious introduction to reinforcement learning.

by Stefano P

•May 19, 2020

This course is very rich of both mathematical and practical concepts, and it actually provides you with powerful tools to understand and use Reinforcement Learning. So far, it is the most interesting course in this specialization. Lectures are very clear and they often explain more deeply some concepts you find in the text book. Quizzes are challenging and well constructed.

by Sebastian P B

•Dec 02, 2019

This was a very good and though course. The content in this course is perfect to get yourself the necessary bases in order to start getting into deep RL. It doesn't really explain that far, but at the end you will have a basic idea of how deep learning can be used with RL. Enough to start reading papers about it or to watch other lectures focused on that topic.

by Zhang d

•May 07, 2020

This course is amazing and wonderful, teaching us the knowledge to use function approximation to solve the vaule and policy estimation. Compared to the preceding tabular presentation, function approximation is appropriate for the reality problem and makes RL more powerful and interesting. I am looking foward to learning more skills in the RL area!

by Jesse W

•Jul 29, 2020

This is a rigorous but clear course in using function approximation to calculate (rather than tabulate) state values and policies in reinforcement learning applications. The videos and assignments are well-constructed and instructive, and the free online textbook is great as well.

by Alvaro M A

•Apr 03, 2020

Excellent course. You'll learn how to apply techniques like Neural Networks to Reinforcement Learning Agents. The assignments are very well designed, and they have the right difficulty so you can learn the most fundamental concepts of the course.

by Surya K S

•Apr 30, 2020

Very well made course. This helped me build Agents for our mobile board game! I'd like some more practical tips as well though, like how to make algorithms converge and things to try out. Other than that, I recommend this to every RL enthusiast.

by Lim G

•May 11, 2020

I enjoyed the course because the content delivery was clear and concise. The hands-on assignment helped me better understand the concepts that were taught. I was able to draw connections and link between textbook and hands-on experience.

by Thomas G

•Apr 21, 2020

A very ambitious course where you have to invest a lot in reading the book but therefore you also learn a lot. I prefer more of those advanced courses here on Coursera.

The course is a very good complement to the book from Sutton.

by Mateusz K

•Oct 29, 2019

Its got a great variety of very applicable examples, use cases, and assignments. May be tough if people don't quite understand how neural networks work, so I suggest having a basic understanding of NN for parts of this course.

by Steven H

•Jul 10, 2020

Excellent course! The assignment could be improved by adding input checking in methods with one-hot encoding of state as input. Which I suffered when I forgot to use the one-hot encoding and spent much time debugging.

by Fred A

•Jun 09, 2020

These series of courses provide one of the best materials for an introduction to reinforcement learning and optimal control. If you are motivated to learn and challenge yourself with RL, don't look elsewhere.

by Wojtek P

•Apr 12, 2020

Difficult but excellent and impressing. Human being is incredible creating such ideas. This course shows a way to the state when all such ingenious ideas will be created by self learning algorithms.

by Antonio C

•Dec 02, 2019

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.

by Sandesh J

•Jun 25, 2020

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!

by Ding L

•Jun 01, 2020

I had been reading the book of Reinforcement Learning An Introduction by myself. This class helped me to finish the study with a great learning environment. Thank you, Martha and Adam!