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

Geo-contextual Service for Operative News Searching and Gatheringwith Neural Network Using

Critical news collection and searching methods are considered. Internet based service of collecting and searching critical news described in the article. Its structural scheme is presented and algorithms of work are desc...

Extension for searching and removing malicious or unnecessary information in the internet browser

In this article software for searching and removing harmful or unnecessary information is described. Goals, objectives and scope of such an extension are defined

The examination of sentence and word length in the writing of Roman Ivanychuk

The article is dedicated to one of the most important areas of quantitative studies of language and speech that is the study of information and statistical properties of text. The length of sentences and words was calcul...

Information model of sociological research in the web environment

This paper is devoted to solving the task of creation the consolidated information resource for sociological research. Show the consolidated resource on which it will be designed and created.

Definition of the extended Galois field GF(dm) with multiplier minimal hardware complexity

The paper compares realised on modern FPGA Galois fields multipliers hardware costs to select Galois field GF(dm) with approximately the same number of elements and the lowest multiplier hardware complexity. The total in...

Download PDF file
  • EP ID EP617419
  • DOI -
  • Views 159
  • 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