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

Formal model of information resources processing in the electronic content commerce systems

The main problems of electronic content commerce are analyzed and functional services of commercial content management are explored. The proposed method gives an opportunity to create an instrument of information resourc...

Generalized description of contrast of image elements

The problem of image quality assessment in the transmission and processing of video data in information and telecommunication systems is considered. The task of no-reference measurement of contrast of two image elements...

Statistical signal processing of acoustic emission and their parameters

The methodological principles of the processing of acoustic emission signals for nondestructive testing of metal and observing the dynamics of developing defects. Statistical analysis of information AE signal parameters...

Ranking factors online resources search engine Google

The paper describes the main factors influencing the design features of high rating resources according to the algorithms search engine Google. The analysis of known technologies and methods of evaluating online resource...

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...

Download PDF file
  • EP ID EP617419
  • DOI -
  • Views 136
  • 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