Name: Fundamentals of Reinforcement Learning
Brand: University of Alberta
Availability: OnlineOnly
Rating: 4.8 (687 reviews)

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

星

2,881 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....

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

创建者 Leigh M

•

Feb 18, 2025

I felt like the videos didn't really provide any intuition, rather were just a repeat of the text book.

创建者 mehryar m

•

Jul 16, 2021

It was quite comperhensive and intuitive one !

创建者 KAUSHIKKUMAR K R

•

Sep 27, 2020

I automatically transferred to Auditing mode.

创建者 Vadim A

•

Apr 14, 2020

More explanations to theory would be nice.

创建者 Jeel V

•

Jun 13, 2020

More details in teaching concepts

创建者 Lasitha R

•

Jan 26, 2025

Good

创建者 Marju P

•

Jul 30, 2021

The course was disappointing for two reasons: poor instruction and poor content. I was expecting a high quality course from Coursera, but was instead finding myself with instructors that simply read a textbook to you. The instructors did not provide any added value. They read the book, even used the exact same examples and slides as in the book. Moreover, this was done in a a boring monotone way. The instructors seemed frozen still, eyes glazed over (with boredom?) with the exception of their lips that moved as they read the slides. Good instruction includes giving more value than just reading a book: new and different examples, different explanations, or at least different wording, personal commentary, sharing own intuition, and linking material to the broader world, making connections between ideas. All of this was missing. Furthermore, the course is not inclusive. The few examples that were chosen were applications to chess and golf. In other words, activities of the privileged few. RL is highly relevant in our world where AI solutions are springing up in all areas of life. There is a wealth of examples that are relatable to a wide variety of people. Instead, by choosing golf and chess, the instructors are alienating the majority of their students. This is in stark contract to Coursera's own mission of expanding and promoting access to high quality education for ALL people regardless of their background (including socio-economic background). The course could be improved by adding content (commentary, explanations, examples, discussions) that has not appeared in the book. Relating this content in a student friendly manner (not monotonically reading slides). In short, the instructors should follow the basics of modern provably effective teaching practices.

创建者 Hung N

•

Oct 9, 2023

The videos are most likely talk about the content in the book without any extra value in explanation. For me, it took a lot of effort to read the book, refers other resources to understand the content.