Matrix stochastic game with Q-learning
Journal Title: Vìsnik Nacìonalʹnogo unìversitetu "Lʹvìvsʹka polìtehnìka". Serìâ Ìnformacìjnì sistemi ta merežì - Year 2015, Vol 814, Issue
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
- EP ID EP617419
- DOI -
- Views 154
- Downloads 0
The defining of sample size for statistical analysis of texts
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. An attempt was made to establish Cheremshyna...
Ontology data cleansing
This article describes the steps to clear data in the DSS. The ontology concepts of clear data were proposed and described. The analysis of methods and data cleansing technology were carried out at every stage of the pro...
Conceptualisation of notions “model” and “modelling” in scientific studies
Some particular aspects of modeling method in scientific research have been outlined in the article. Philosophic maxims on which the model concept is based were suggested. The generalized model definition, its characteri...
Forecasting network requests numbers to cloud application
The article contains analysis of existing time series forecast methods. It is estimated how these methods fit to time series of network requests to a cloud application. Optimal forecasting methods have been chosen for di...
Information system interaction of universities with social environment internet
This article implemented a formal accounting structure of the university. This article describes the information model of each component in the form of a database diagram "entity-relationship". Specifically described dat...