Markov decision process toolbox

Author

Shan Peng ; Li Ran ; Ning Sheng-hua ; Yang Qin

Author_Institution

Dept. Electron. Inf. & Control Eng., Guangxi Univ. of Technol., Liuzhou, China

fYear

2009

fDate

18-20 Sept. 2009

Firstpage

123

Lastpage

128

Abstract

Markov decision process is optimal policy-making process which is based on the Markov process theory of random dynamical systems. It is also a theoretical tool to study optimization problems about multi-stage policy-making process in random environment. For its wide range of applications, developing the Markov decision process toolbox is of great significance for the scientific computing software SCILAB. Markov policy process consists of three main criterions: the expected total reward criterion, discount criterion and average criterion. Finally, taking the toys manufacturers as the example the effectiveness of the method is tested.

Keywords

Markov processes; decision theory; mathematics computing; natural sciences computing; Markov decision process toolbox; SCILAB; average criterion; discount criterion; expected total reward criterion; multistage policy-making process; optimal policy-making process; random dynamical system; scientific computing software; toys manufacturers; Application software; Control systems; Dynamic programming; Macroeconomics; Markov processes; Mathematical model; Scientific computing; Software tools; Stochastic systems; Toy manufacturing industry; Markov decision process; SCILAB; average criterion; discount criterion; expectation total reward criterion;

fLanguage

English

Publisher

ieee

Conference_Titel

Open-source Software for Scientific Computation (OSSC), 2009 IEEE International Workshop on

Conference_Location

Guiyang

Print_ISBN

978-1-4244-4452-6

Electronic_ISBN

978-1-4244-4453-3

Type

conf

DOI

10.1109/OSSC.2009.5416859

Filename

5416859