RISK-SENSITIVE LQR PROBLEMS WITH EXPONENTIAL NOISE

Shortanbaiuly, Olzhas

Система будет остановлена для регулярного обслуживания. Пожалуйста, сохраните рабочие данные и выйдите из системы.

dc.contributor.author	Shortanbaiuly, Olzhas
dc.date.accessioned	2024-06-07T10:57:24Z
dc.date.available	2024-06-07T10:57:24Z
dc.date.issued	2024-04-26
dc.identifier.citation	Shortanbaiuly, O. (2024). Risk-sensitive LQR problems with exponential noise. Nazarbayev University School of Sciences and Humanities	en_US
dc.identifier.uri	http://nur.nu.edu.kz/handle/123456789/7791
dc.description.abstract	This 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.language.iso	en	en_US
dc.publisher	Nazarbayev University School of Sciences and Humanities	en_US
dc.rights	Attribution-NonCommercial-ShareAlike 3.0 United States	*
dc.rights.uri	http://creativecommons.org/licenses/by-nc-sa/3.0/us/	*
dc.subject	LQR problem	en_US
dc.subject	Markov Decision Process	en_US
dc.subject	Average-Value-at-Risk	en_US
dc.subject	Approximate Dynamic Programming	en_US
dc.subject	Exponential Distribution	en_US
dc.subject	Type of access: Open Access	en_US
dc.title	RISK-SENSITIVE LQR PROBLEMS WITH EXPONENTIAL NOISE	en_US
dc.type	Master's thesis	en_US
workflow.import.source	science