Chevron Left
返回到 Fundamentals of Reinforcement Learning

学生对 University of Alberta 提供的 Fundamentals of Reinforcement Learning 的评价和反馈

4.8
2,886 个评分

课程概述

Reinforcement Learning is a subfield of Machine Learning, but is also a general purpose formalism for automated decision-making and AI. This course introduces you to statistical learning techniques where an agent explicitly takes actions and interacts with the world. Understanding the importance and challenges of learning agents that make decisions is of vital importance today, with more and more companies interested in interactive agents and intelligent decision-making. This course introduces you to the fundamentals of Reinforcement Learning. When you finish this course, you will: - Formalize problems as Markov Decision Processes - Understand basic exploration methods and the exploration/exploitation tradeoff - Understand value functions, as a general-purpose tool for optimal decision-making - Know how to implement dynamic programming as an efficient solution approach to an industrial control problem This course teaches you the key concepts of Reinforcement Learning, underlying classic and modern algorithms in RL. After completing this course, you will be able to start using RL for real problems, where you have or can specify the MDP. This is the first course of the Reinforcement Learning Specialization....

热门审阅

MN

Apr 11, 2024

The concepts may sound confusing in the beginning, but as you go forward you find it interesting and understanding. I suggest you completely read the reading assignments before watching the videos.

KS

Sep 1, 2019

All the concepts were well explained and this course was perhaps the best I have found for RL.Great efforts have been put into making the course and It goes well in line with the suggested textbook.

筛选依据:

601 - Fundamentals of Reinforcement Learning 的 625 个评论(共 688 个)

创建者 Muhammed A Ç

Jul 15, 2021

Without reading the recommended book, course material would not be sufficient. Coding exercises quite good and also quizzes' are suitable for beginner level

创建者 Naresh T

Mar 28, 2020

Good understanding of the fundamentals and aptly paced. The programming assignments were very good if there were more like that the course could get better

创建者 aysegul

Jun 9, 2021

It brings general understanding. The main focus is reading the book. Assignments are about the introduction, help to understand, but they can be improved.

创建者 Romesh M P

May 21, 2020

I really enjoyed the course, especially the guest segments (I got to know important people from that). Presenters did a good job but can be more relaxed.

创建者 Jo K

Jan 28, 2021

Very good introductory course for reinforcement learning. Good coding assignment, but could add more visual representation to understand the transition.

创建者 Marcello M

Aug 13, 2020

Very good theoretical contents, pretty much in line with the textbook - practical coding parts are mostly exercises of conversion of equations into code

创建者 Mahmmoud M

Sep 29, 2019

However, Missing the lectures of slide, the supported book is very good. The lectures are very simple and one can finish fast.

Thanks for teaching team.

创建者 Chirag A S

Jun 20, 2023

The conceptual learning through the course is really good, however the coding assignments would be much better if they were to be a bit more intuitive

创建者 Prakhar J

Aug 28, 2020

The content was very well organized, but applications could have been better understood using more complex numerical algorithms and more assignments.

创建者 Amit M

Feb 13, 2024

It is a difficult course. Will be useful to have more intuitive discussion + more programming assignments - hard to see how all the terms play out.

创建者 krishna c

Dec 31, 2020

The guest lecture on truck fleet management was not great, the teacher tried to cover lot more material in a short time in the video then possible.

创建者 Ramakrishnan.K

Jun 21, 2020

The fundamentals of Bandits and MDPs are well covered. A major plus is the way we are made to read the text book before attending the lectures.

创建者 Shailesh

Jul 18, 2023

A little more clarity while describing and solving the problem or examples please as I was stuck sometimes figuring out basic misconceptions.

创建者 Slav K

Jan 4, 2021

A solid start with theoretical fundament. Assignment 2 was too cumbersome, lacking the description of actions encoded in the assignment.

创建者 Petru R

Jan 20, 2021

More Python examples are needed throughout the lessons.

Not only at the final. No proper introduction to DL Python library is given.

创建者 NEHUL B

Sep 9, 2020

I was hoping for a bit more practical application too, but this course does a solid job at teaching you the theory thoroughly.

创建者 Matthew C

Aug 24, 2019

Auto-grading of programming exercises did not work that well, but other than that, it was very instructive and well presented.

创建者 Mark C

Sep 27, 2021

The course is mostly a repeat of the text book. Fortunately the text book is free. Regardless, the material is interesting.

创建者 Muhammad U S

Oct 11, 2020

Highly recommended for the beginners. If you are new to RL then this course is the best along with Sutton and Barto Book.

创建者 Matthew W

Jul 17, 2021

pretty good course for RL basics, not as in depth as the book and programming assignments were too easy, but good intro

创建者 Parham

Jul 6, 2020

there is so many great fundamental stuff here, with deep theoric background, but it lacks some practical approach

创建者 Christopher C

Sep 8, 2019

I thought the lectures were informative, but the pacing could have been a bit faster to get through more content.

创建者 Rafael V M

Jul 15, 2020

Excellent course, with several practical examples of the theory being explained. I found week 3 a little dense.

创建者 BALSHER S

Jul 9, 2020

Week 3 should be improved a bit. It is a bit confusing to understand. Btw Great course. Keep the good work up.

创建者 sharmili s

Apr 15, 2020

Quizzes and assignments are a bit challenging. It might be easier if questions are better elucidated.