RISK-SENSITIVE LQR PROBLEMS WITH EXPONENTIAL NOISE

Simple item page
dc.contributor.authorShortanbaiuly, Olzhas
dc.date.accessioned2024-06-07T10:57:24Z
dc.date.available2024-06-07T10:57:24Z
dc.date.issued2024-04-26
dc.description.abstractThis thesis is about optimal control of Markov Decision Processes and solving risk-sensitive cost minimization and reward maximization problems, specifically, the Linear Quadratic Regulator (LQR) problem with Average-Value-at-Risk criteria. The problem is solved for different risk levels, different random noises (theoretical and sampled), and using different methods: analytical and approximate dynamic programming. The obtained results were analyzed and discussed for the presence of certain patterns and trends. The results show that approximate dynamic programming is a very accurate method for solving risk-sensitive LQR problems with exponential noise.en_US
dc.identifier.citationShortanbaiuly, O. (2024). Risk-sensitive LQR problems with exponential noise. Nazarbayev University School of Sciences and Humanitiesen_US
dc.identifier.urihttp://nur.nu.edu.kz/handle/123456789/7791
dc.language.isoenen_US
dc.publisherNazarbayev University School of Sciences and Humanitiesen_US
dc.rightsAttribution-NonCommercial-ShareAlike 3.0 United States*
dc.rights.urihttp://creativecommons.org/licenses/by-nc-sa/3.0/us/*
dc.subjectLQR problemen_US
dc.subjectMarkov Decision Processen_US
dc.subjectAverage-Value-at-Risken_US
dc.subjectApproximate Dynamic Programmingen_US
dc.subjectExponential Distributionen_US
dc.subjectType of access: Open Accessen_US
dc.titleRISK-SENSITIVE LQR PROBLEMS WITH EXPONENTIAL NOISEen_US
dc.typeMaster's thesisen_US
workflow.import.sourcescience

Files

Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
Olzhas_Shortanbaiuly_Thesis_Revised.pdf
Size:
671.29 KB
Format:
Adobe Portable Document Format
Description:
Thesis
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
6.28 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

Theses and Dissertations