Necessary and sufficient conditions for a bounded solution to the optimality equation in average reward Markov decision chains

DOI10.1016/0167-6911(88)90043-6zbMath0645.90099OpenAlexW2094140762MaRDI QIDQ1103532

Rolando Cavazos-Cadena

Publication date: 1988

Published in: Systems \& Control Letters (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/0167-6911(88)90043-6

zbMATH Keywords

countable state spaceoptimal stationary policiesaverage reward optimality equationdiscrete time Markov decision processbounded measurable reward functionsimultaneous Doeblin condition

Mathematics Subject Classification ID

Markov and semi-Markov decision processes (90C40)

Related Items (14)

Unnamed Item ⋮ Optimality equations and inequalities in a class of risk-sensitive average cost Markov decision chains ⋮ 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 ⋮ Strong 1-optimal stationary policies in denumerable Markov decision processes ⋮ A note on the convergence rate of the value iteration scheme in controlled Markov chains ⋮ Sample-Path Optimal Stationary Policies in Stable Markov Decision Chains with the Average Reward Criterion ⋮ Recent results on conditions for the existence of average optimal stationary policies ⋮ A counterexample on the optimality equation in Markov decision chains with the average cost criterion ⋮ A note on the vanishing interest rate approach in average Markov decision chains with continuous and bounded costs ⋮ Existence of optimal stationary policies in average reward Markov decision processes with a recurrent state ⋮ Solutions of the average cost optimality equation for Markov decision processes with weakly continuous kernel: the fixed-point approach revisited ⋮ Remarks on the existence of solutions to the average cost optimality equation in Markov decision processes ⋮ Nonstationary value iteration in controlled Markov chains with risk-sensitive average criterion

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• A new condition for the existence of optimal stationary policies in average cost Markov decision processes
• Necessary conditions for the optimality equation in average-reward Markov decision processes
• Existence of optimal stationary policies in average reward Markov decision processes with a recurrent state
• Two competing queues with linear costs and geometric service requirements: the μc-rule is often optimal
• A note on simultaneous recurrence conditions on a set of denumerable stochastic matrices

This page was built for publication: Necessary and sufficient conditions for a bounded solution to the optimality equation in average reward Markov decision chains