Risk-sensitive Average Optimality in Markov Decision Processes

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F67985556%3A_____%2F18%3A00502902" target="_blank" >RIV/67985556:_____/18:00502902 - isvavai.cz</a>

Result on the web

<a href="http://dx.doi.org/10.14736/kyb-2018-6-1218" target="_blank" >http://dx.doi.org/10.14736/kyb-2018-6-1218</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.14736/kyb-2018-6-1218" target="_blank" >10.14736/kyb-2018-6-1218</a>

Result language

angličtina

Original language name

Risk-sensitive Average Optimality in Markov Decision Processes

Original language description

In this note attention is focused on finding policies optimizing risk-sensitive optimality criteria in Markov decision chains. To this end we assume that the total reward generated by the Markov process is evaluated by an exponential utility function with a given risk-sensitive coefficient. The ratio of the first two moments depends on the value of the risk-sensitive coefficient, if the risk-sensitive coefficient is equal to zero we speak on risk-neutral models. Observe that the first moment of the generated reward corresponds to the expectation of the total reward and the second central moment of the reward variance. For communicating Markov processes and for some specific classes of unichain processes long run risk-sensitive average reward is independent of the starting state. In this note we present necessary and sufficient condition for existence of optimal policies independent of the starting state in unichain models and characterize the class of average risk-sensitive optimal policies.

Czech name

—

Czech description

—

Type

J_imp - Article in a specialist periodical, which is included in the Web of Science database

CEP classification

—

OECD FORD branch

10103 - Statistics and probability

Project

<a href="/en/project/GA18-02739S" target="_blank" >GA18-02739S: Stochastic Optimization in Economic Processes</a><br>

Continuities

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Publication year

2018

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Name of the periodical

Kybernetika

ISSN

0023-5954

e-ISSN

—

Volume of the periodical

54

Issue of the periodical within the volume

6

Country of publishing house

CS1 -

Number of pages

13

Pages from-to

1218-1230

UT code for WoS article

000457070200009

EID of the result in the Scopus database

—