Markov Decision Problems Where Means Bound Variances

Loading...
Thumbnail Image
Penn collection
Operations, Information and Decisions Papers
Degree type
Discipline
Subject
Markov decision problems
variance bounds
optimal total reward
Business Administration, Management, and Operations
Finance and Financial Management
Operations and Supply Chain Management
Funder
Grant number
License
Copyright date
Distributor
Related resources
Author
Arlotto, Alessandro
Gans, Noah
Steele, John M
Contributor
Abstract

We identify a rich class of finite-horizon Markov decision problems (MDPs) for which the variance of the optimal total reward can be bounded by a simple linear function of its expected value. The class is characterized by three natural properties: reward nonnegativity and boundedness, existence of a do-nothing action, and optimal action monotonicity. These properties are commonly present and typically easy to check. Implications of the class properties and of the variance bound are illustrated by examples of MDPs from operations research, operations management, financial engineering, and combinatorial optimization.

Advisor
Date Range for Data Collection (Start Date)
Date Range for Data Collection (End Date)
Digital Object Identifier
Series name and number
Publication date
2014-07-01
Journal title
Operations Research
Volume number
Issue number
Publisher
Publisher DOI
Journal Issue
Comments
Recommended citation
Collection