The convergence of value iteration in average cost Markov decision chains

DOI10.1016/0167-6377(96)00018-1zbMath0865.90134MaRDI QIDQ2564235

Linn I. Sennott

Publication date: 7 January 1997

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

Full work available at URL: https://doi.org/10.1016/0167-6377(96)00018-1

zbMATH Keywords

stochastic dynamic programming; value iteration; countable state space; Markov decision chain; minimum long-run expected average cost

Mathematics Subject Classification ID

90C40: Markov and semi-Markov decision processes

Related Items

The value iteration method for countable state Markov decision processes

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Another set of conditions for average optimality in Markov control processes
• On strong average optimality of Markov decision processes with unbounded costs
• Comparing recent assumptions for the existence of average optimal stationary policies
• Optimal control of diffusion processes with reflection
• 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
• Linear Programming and Average Optimality of Markov Control Processes on Borel Spaces—Unbounded Costs
• Discrete-Time Controlled Markov Processes with Average Cost Criterion: A Survey