Home
Resource
Methods of temporal differences for risk-averse dynamic programming and learning
PDF
PDF format is widely accepted and good for printing.
Plug-in required
PDF-1(697.60 kb)
Citation & Export
View Usage Statistics
Staff View

Citation & Export
Hide

Simple citation

Kose, Umit. Methods of temporal differences for risk-averse dynamic programming and learning. Retrieved from https://doi.org/doi:10.7282/t3-5b3y-5c51

Export

Click here for information about Citation Management Tools at Rutgers.

Statistics
Hide

Description

TitleMethods of temporal differences for risk-averse dynamic programming and learning
NameKose, Umit (author); Ruszczynski, Andrzej (chair); Eckstein, Jonathan (internal member); Gurbuzbalaban, Mert (internal member); Dentcheva, Darinka (outside member); Rutgers University; Graduate School - Newark
Date Created2020
Other Date2020-05 (degree)
SubjectManagement
Extent1 online resource (vi, 44 pages)
DescriptionStochastic sequential decision-making problems are generally modeled and solved as Markov decision processes. When the decision-makers are risk-averse, their risk-aversion can be incorporated into the model using dynamic risk-measures. Such risk-averse Markov decision processes can be theoretically solved by specialized dynamic programming methods. However, when the state space of the system becomes very large, then such methods become impractical.

We consider reinforcement learning with performance evaluated by a dynamic risk measure for Markov decision processes. We use a linear value function approximation scheme and construct a projected risk-averse dynamic programming equation that involves this scheme. We study the properties of this equation. To solve this equation, we propose risk-averse counterparts of the methods of temporal differences and we prove their convergence with probability one. We also perform an empirical study on a complex transportation problem where we demonstrate that the risk-averse methods of temporal differences outperform the well known risk-neutral methods in terms of average profit over time.
NotePh.D.
NoteIncludes bibliographical references
Genretheses, ETD doctoral
Persistent URLhttps://doi.org/doi:10.7282/t3-5b3y-5c51
LanguageEnglish
CollectionGraduate School - Newark Electronic Theses and Dissertations
Organization NameRutgers, The State University of New Jersey
RightsThe author owns the copyright to this work.
Version 8.5.5
Rutgers University Libraries - Copyright ©2024