Decision Making and Reinforcement Learning

Columbia University

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.

Certificate Available ✔

Get Started / More Info
Decision Making and Reinforcement Learning
More Algorithms Courses

Introduction to Discrete Mathematics for Computer Science

University of California San Diego

Discrete Mathematics is the language of Computer Science. One needs to be fluent in it to work in many fields including data science, machine learning, and software...

Artificial Intelligence Data Fairness and Bias


In this course, we will explore fundamental issues of fairness and bias in machine learning. As predictive models begin making important decisions, from college...

Operations Research (2): Optimization Algorithms

National Taiwan University

Operations Research (OR) is a field in which people use mathematical and engineering methods to study optimization problems in Business and Management, Economics,...


Peking University

学了C/C++ 语言,我们已经会编程解题了,那怎么用来处理实际的问题呢? 怎么设计数据结构来有效地管理企业人员?如何编写程序没让人才和岗位达到最佳匹配?如何安排旅行计划,找到最佳行程路径?这些学习、工作、生活中常常困扰我们的问题,你将在《数据结构基础》课程中找到答案。...