Back to Decision Making and Reinforcement Learning
Columbia University

Decision Making and Reinforcement Learning

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.

Status: Markov Model
Status: Artificial Intelligence and Machine Learning (AI/ML)
IntermediateCourse47 hours

Featured reviews

QN

5.0Reviewed Jan 20, 2024

Very good introductory and basic to Reinforcement Learning. But programming assignments need more careful compilation and more attention to detail!

SH

5.0Reviewed Jul 9, 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.

All reviews

Showing: 5 of 5

Natthaphon Choomphon-anomakhun
5.0
Reviewed Nov 21, 2024
Christian Baptist
4.0
Reviewed Nov 16, 2023
Stefan Hendrickx
5.0
Reviewed Jul 10, 2023
quy dau nguyen
5.0
Reviewed Jan 21, 2024
Yovian
1.0
Reviewed Oct 12, 2024