On strong average optimality of Markov decision processes with unbounded costs

DOI10.1016/0167-6377(92)90040-AzbMath0768.90085OpenAlexW1970207423MaRDI QIDQ1197886

Steven I. Marcus, Mrinal K. Ghosh

Publication date: 16 January 1993

Published in: Operations Research Letters (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/0167-6377(92)90040-a

zbMATH Keywords

countable state spacecompact action spaceaverage Markov decision processesstable stationary strategystrong average optimal

Mathematics Subject Classification ID

Markov and semi-Markov decision processes (90C40)

Related Items (5)

Average optimality in dynamic programming on Borel spaces -- unbounded costs and controls ⋮ Denumerable controlled Markov chains with average reward criterion: Sample path optimality ⋮ The convergence of value iteration in average cost Markov decision chains ⋮ The value iteration method for countable state Markov decision processes ⋮ Unnamed Item

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Necessary conditions for the optimality equation in average-reward Markov decision processes
• On optimality criteria for dynamic programs with long finite horizons
• Stochastic optimal control. The discrete time case
• Average cost Markov decision processes: Optimality conditions
• Ergodic and adaptive control of nearest-neighbor motions
• Comparing recent assumptions for the existence of average optimal stationary policies
• Adaptive Markov control processes
• Average Cost Semi-Markov Decision Processes and the Control of Queueing Systems
• Denumerable Undiscounted Semi-Markov Decision Processes with Unbounded Rewards
• On Minimum Cost Per Unit Time Control of Markov Chains
• Control of Markov Chains with Long-Run Average Cost Criterion: The Dynamic Programming Equations
• Average Cost Optimal Stationary Policies in Infinite State Markov Decision Processes with Unbounded Costs
• Optimal control of service rates in networks of queues
• Denumerable State Markovian Decision Processes-Average Cost Criterion
• A Solution to a Countable System of Equations Arising in Markovian Decision Processes
• Semi-Markov Decision Processes with Unbounded Rewards
• Cumulative quantum work-deficit versus entanglement in the dynamics of an infinite spin chain

This page was built for publication: On strong average optimality of Markov decision processes with unbounded costs