SEMI-MARKOV DECISION PROCESSES WITH INCOMPLETE STATE OBSERVATION : AVERAGE COST CRITERION

DOI10.15807/jorsj.24.95zbMath0488.90073OpenAlexW4243667875MaRDI QIDQ3950328

Kazuyoshi Wakuta

Publication date: 1981

Published in: Journal of the Operations Research Society of Japan (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.15807/jorsj.24.95

zbMATH Keywords

infinite horizonsemi-Markov decision processmethod of successive approximationsaverage cost criterionfinite action spacecountable state spaceincomplete state observationBorel state semi- Markov decision processcomplete state observationexistence conditions for stationary optimal policies

Mathematics Subject Classification ID

Markov renewal processes, semi-Markov processes (60K15) Markov and semi-Markov decision processes (90C40)

Related Items (2)

Partially observed semi-Markov zero-sum games with average payoff ⋮ Adaptive control of Markov processes with incomplete state information and unknown parameters

This page was built for publication: SEMI-MARKOV DECISION PROCESSES WITH INCOMPLETE STATE OBSERVATION : AVERAGE COST CRITERION