markov decision problems
Recently Published Documents


TOTAL DOCUMENTS

98
(FIVE YEARS 4)

H-INDEX

13
(FIVE YEARS 1)

Author(s):  
Jean Walrand

AbstractThere is a class of control problems that admit a particularly elegant solution: the linear quadratic Gaussian (LQG) problems. In these problems, the state dynamics and observations are linear, the cost is quadratic, and the noise is Gaussian. Section 14.1 explains the theory of LQG problems when one observes the state. Section 14.2 discusses the situation when the observations are noisy and shows the remarkable certainty equivalence property of the solution. Section 14.3 explains how noisy observations affect Markov decision problems.


2019 ◽  
Vol 279 (1-2) ◽  
pp. 251-270 ◽  
Author(s):  
Yevgeny Tsodikovich ◽  
Ehud Lehrer

Sign in / Sign up

Export Citation Format

Share Document