Risk-sensitive Average Optimality in Markov Decision Processes

Kód výsledku v 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>

Výsledek na webu

<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>

Jazyk výsledku

angličtina

Název v původním jazyce

Risk-sensitive Average Optimality in Markov Decision Processes

Popis výsledku v původním jazyce

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.

Název v anglickém jazyce

Risk-sensitive Average Optimality in Markov Decision Processes

Popis výsledku anglicky

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.

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

10103 - Statistics and probability

Projekt

<a href="/cs/project/GA18-02739S" target="_blank" >GA18-02739S: Stochastická optimalizace v ekonomických procesech</a><br>

Návaznosti

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

Rok uplatnění

2018

Kód důvěrnosti údajů

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

Název periodika

Kybernetika

ISSN

0023-5954

e-ISSN

—

Svazek periodika

54

Číslo periodika v rámci svazku

6

Stát vydavatele periodika

CS1 -

Počet stran výsledku

13

Strana od-do

1218-1230

Kód UT WoS článku

000457070200009

EID výsledku v databázi Scopus

—