Name: Decision Making and Reinforcement Learning
Brand: Columbia University
Availability: OnlineOnly
Rating: 4.3 (5 reviews)

返回到 Decision Making and Reinforcement Learning

学生对 Columbia University 提供的 Decision Making and Reinforcement Learning 的评价和反馈

4.3

星

20 个评分

课程概述

This course is an introduction to sequential decision making and reinforcement learning. We start with a discussion of utility theory to learn how preferences can be represented and modeled for decision making. We first model simple decision problems as multi-armed bandit problems in and discuss several approaches to evaluate feedback. We will then model decision problems as finite Markov decision processes (MDPs), and discuss their solutions via dynamic programming algorithms. We touch on the notion of partial observability in real problems, modeled by POMDPs and then solved by online planning methods. Finally, we introduce the reinforcement learning problem and discuss two paradigms: Monte Carlo methods and temporal difference learning. We conclude the course by noting how the two paradigms lie on a spectrum of n-step temporal difference methods. An emphasis on algorithms and examples will be a key part of this course....

1 - Decision Making and Reinforcement Learning 的 5 个评论（共 5 个）

创建者 Natthaphon C

•

Nov 21, 2024

Professor Tony Dear provides clear explanations of reinforcement learning, starting from the basics. The course includes numerous examples with simple computations that effectively reinforce your understanding of the concepts. The quizzes are appropriately challenging, while the programming assignments are relatively straightforward. Overall, this is a great and enjoyable course. I learned a lot and highly recommend it. Thank you!

创建者 Christian B

•

Nov 16, 2023

Good Course, you will be teached a lot about Reinforcement learning and Decision making. The Quiz and the Programming Assignments help a lot with this. For me personally the Videos were sometimes a bit fast but thats not a problem because you can pause and rewatch them. The only critic I have to mention is that some of the programming tasks are not not sufficiently described or explained. I think you could learn faster if you dont bother with figuring out what to implement and what to do. All in all the course is good and I would recommend it for someone who wants to start to learn about Reinforcement Learning.

创建者 Stefan H

•

Jul 10, 2023

Well-structured course that provides a great introduction to methodologies used in reinforcement learning. I am now eager to experiment more in my own time, to consolidate what I have learned.