Matrix stochastic game with Q-learning

Abstract

The model of matrix stochastic game for decision-making in the conditions of uncertainty is developed. The method of Q-learning for stochastic game solving with a priori unknown gains matrices is offered. The formulation of a game problem is executed. The Markovian recurrent method and algorithm for the game solving are described. Results of computer modelling of stochastic game with Q-learning are received and analysed.

Authors and Affiliations

Petro Kravets

Keywords

Related Articles

Mathematical methods and applied information technologies of modeling, translation and training for the Ukrainian sign language

In the scientific paper a number of important scientific and applied tasks related to the development of mathematical methods and the formation of a complex of applied information technologies of modeling, processing and...

Analytical approaches for definition of functions with variable period and information technology for determining of Fourier coefficients

Main achievements of function theory with variable period have been described. The tasks aimed at their further study, namely the task of functions with variable period “approximation” Fourier series, and development the...

Mobile information technologies of user navigation in buildings

The article is devoted to the indoors positioning technology and user mobile positioning devices. The possibilities of computer technology of indoors positioning of the device when navigating the user through the territo...

Decision Support System for Financial Markets’ Investment Risks Analysis

The article describes the features of the VaR methodology for assessing investment risks in the financial markets of securities. Developed decision support information system allows to calculate expected and unexpected l...

Crypto-protection System of Ble-based Communication Channel for Iot Devices and Mobile Computational Device

Bluetooth communication channel protection for IOT devices and IOS based devices considered in the article. Channel encryption and shared key distribution in unsaved nvironment analyzed. The proposed protection system is...

Download PDF file
  • EP ID EP617419
  • DOI -
  • Views 160
  • Downloads 0

How To Cite

Petro Kravets (2015). Matrix stochastic game with Q-learning. Vìsnik Nacìonalʹnogo unìversitetu "Lʹvìvsʹka polìtehnìka". Serìâ Ìnformacìjnì sistemi ta merežì, 814(), 71-80. https://europub.co.uk./articles/-A-617419