Chevron Left
返回到 A Complete Reinforcement Learning System (Capstone)

学生对 阿尔伯塔大学 提供的 A Complete Reinforcement Learning System (Capstone) 的评价和反馈

4.7
552 个评分
116 条评论

课程概述

In this final course, you will put together your knowledge from Courses 1, 2 and 3 to implement a complete RL solution to a problem. This capstone will let you see how each component---problem formulation, algorithm selection, parameter selection and representation design---fits together into a complete solution, and how to make appropriate choices when deploying RL in the real world. This project will require you to implement both the environment to stimulate your problem, and a control agent with Neural Network function approximation. In addition, you will conduct a scientific study of your learning system to develop your ability to assess the robustness of RL agents. To use RL in the real world, it is critical to (a) appropriately formalize the problem as an MDP, (b) select appropriate algorithms, (c ) identify what choices in your implementation will have large impacts on performance and (d) validate the expected behaviour of your algorithms. This capstone is valuable for anyone who is planning on using RL to solve real problems. To be successful in this course, you will need to have completed Courses 1, 2, and 3 of this Specialization or the equivalent. By the end of this course, you will be able to: Complete an RL solution to a problem, starting from problem formulation, appropriate algorithm selection and implementation and empirical study into the effectiveness of the solution....

热门审阅

JJ

Apr 27, 2020

This is the final chapter. It is one of the easiest and it was fun doing that lunar landing project. This specialisation is the best for a person taking baby steps in the reinforcement learning.

CR

Feb 26, 2020

Great course for learning the fundamentals. I liked that it tied into function approximation for deep reinforcement learning. The text book made the fundamental concepts more clear.

筛选依据:

101 - A Complete Reinforcement Learning System (Capstone) 的 117 个评论(共 117 个)

创建者 Yichen W

Dec 4, 2019

The comments given by the auto grader is not informative of the errors causing problem, and not sensitive enough to capture problems with action selection steps based on current state.

创建者 Harold

Jan 13, 2022

It may have been useful to provide less guidance to the students to make sure they develop the required skills. Overall, it was a nice exercise to implement a TD(0) network.

创建者 Pradeep

Jun 5, 2020

Project could be better designed and could be made more fun. The first 3 courses were brilliant. I finished the entire capstone in less than 26-hours to save money!

创建者 Matt S H

Feb 3, 2021

Good project as a capstone. Wish there would have been more work needed from our side of things in terms of coding, but very solid final course for RL.

创建者 Yassine B

May 15, 2020

Great Course. But, it would be much more fun if the programming assignments were implemented in for instance tensorflow or pytorch!

创建者 Sérgio V C

Apr 3, 2021

I give 4 stars because this last course is not as good as the previous ones. No real complaints, but it's not as "complete".

创建者 Akinyele O

Jun 7, 2020

The courses in this specialization are very essential to obtain basic knowledge on reinforcement learning.

创建者 Rafael B

Oct 28, 2021

My unique (possible) critic is the absence of more industry standard packages

创建者 Oscar R R M

Sep 1, 2021

V​ery good exercises and good way to learn about Reinforcement Learning

创建者 Antonio P

Jan 21, 2020

Good course

创建者 Oleksii K

Sep 19, 2020

I wish that this course contained more practical advice.

The video describing the problem and the notebook describing the problem contradict each other in many details.

Also, the name of the course is a bit misleading. Instead of building "A Complete Reinforcement Learning System" and covering all of the building blocks of an RL project, the homeworks were mainly focused on training the agent, very similar to most previous assignments. So it was more about doing the same one thing in more depth rather than doing more different things.

创建者 Stefano P

Aug 9, 2020

The idea of dedicating a whole course to a practical project was indeed very good. However I think that this idea was not exploited as deeply as it could have been. The project itself is actually a notebook just a little longer than usual. I would have left more to do to students, and maybe they could have used lectures to give more explanations and hints for the practical part, or to do some programming together. Anyway, the course is overall fairly good, and it also introduces some new concepts, like experience replay.

创建者 Naoufel E B

Feb 16, 2020

I would have expected to do more of the implementation in the capstone project.

It is still quite useful to go through the details of what is implemented by the instructor for us, but not as effective as having to implement more of it ourselves.

Thanks

创建者 Dustin Z

May 5, 2021

A good review of the material covered in the specialization. I would have liked to see a more thorough parameter study and deeper coverage of the environment wrapper around the OpenAI lunar lander environment.

创建者 Alireza K

Mar 18, 2021

Review videos were tiring for people that had watched previous courses!

创建者 Umut Z

Dec 15, 2019

Could be more detailed in the environment setup

创建者 Manuel V d S

Nov 7, 2019

Not worth it.