Адаптивне керування славкокерованими марковськими та напівмарковськими моделями в дискретному часі

A Bayesian approach to Markov decision process problem [1] under stochastic uncertainty, when unknown transition probabilities are weakly disturbed with disturbances dependent on a decision strategy only is investigated. Observed decision process is assumed to be stationary in discrete time with fin...

Full description

Saved in:
Bibliographic Details
Date:2019
Main Author: Andreev, N. V.
Format: Article
Language:Ukrainian
Published: The National Technical University of Ukraine "Igor Sikorsky Kyiv Polytechnic Institute" 2019
Online Access:http://journal.iasa.kpi.ua/article/view/174306
Tags: Add Tag
No Tags, Be the first to tag this record!
Journal Title:System research and information technologies

Institution

System research and information technologies
Description
Summary:A Bayesian approach to Markov decision process problem [1] under stochastic uncertainty, when unknown transition probabilities are weakly disturbed with disturbances dependent on a decision strategy only is investigated. Observed decision process is assumed to be stationary in discrete time with finite, countable or measurable phase state is based on separation principle of assessment and optimization problems.