Markov Decision Processes with a Borel Measurable Cost Function—The Average Case

DOI10.1287/moor.11.2.309zbMath0607.90087OpenAlexW2134961363MaRDI QIDQ3748085

Masami Kurano

Publication date: 1986

Published in: Mathematics of Operations Research (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1287/moor.11.2.309

zbMATH Keywords

average cost criteriongeneral state and action spacesBorel measurable cost function\(\epsilon \)-optimal stationary policiesPeriodic-stationary policiessequential replacement-model

Mathematics Subject Classification ID

Reliability, availability, maintenance, inspection in operations research (90B25) Inventory, storage, reservoirs (90B05) Programming in abstract spaces (90C48) Markov and semi-Markov decision processes (90C40)

Related Items

Markov decision processes with a minimum-variance criterion ⋮ Recurrence conditions for Markov decision processes with Borel state space: A survey ⋮ On the average cost optimality equation and the structure of optimal policies for partially observable Markov decision processes ⋮ Average Cost Optimality Inequality for Markov Decision Processes with Borel Spaces and Universally Measurable Policies ⋮ STRONG AVERAGE OPTIMALITY FOR CONTROLLED NONHOMOGENEOUS MARKOV CHAINS^* ⋮ Average cost Markov decision processes under the hypothesis of Doeblin ⋮ Semi-Markov decision processes with a reachable state-subset ⋮ Occupation measures in average cost Markov decision processes ⋮ On structural properties of optimal average cost functions in Markov decision processes with Borel spaces and universally measurable policies ⋮ Controlled Markov set-chains under average criteria