Rate of Convergence of Empirical Measures and Costs in Controlled Markov Chains and Transient Optimality

DOI10.1287/MOOR.19.4.955MaRDI QIDQ4698108zbMATH OpenOpenAlexFDO

Authors Ofer Zeitouni, Eitan Altman

Publication date 27 September 1995

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

Full work available at URL https://semanticscholar.org/paper/21ae8e8ac1a2685c1d0672384d6d2fcdbc451a95

zbMATH Keywords

controlled Markov chainsrate of convergencerecurrence conditions

Mathematics Subject Classification ID

Markov and semi-Markov decision processes (90C40)

Recommendations

• Empirical convergence rates for continuous-time Markov chains
• Convergence of the optimal values of constrained Markov control processes
• Convergence rates of Markov chain approximation methods for controlled diffusions with stopping
• A note on the convergence rate of the value iteration scheme in controlled Markov chains
• Constrained Markov control processes with randomized discounted cost criteria: occupation measures and extremal points
• Occupation measures for controlled Markov processes: Characterization and optimality

Cited in

(5)

• Fast convergence to state-action frequency polytopes for MDPs
• How fast do equilibrium payoff sets converge in repeated games?
• Simulation-based optimization of Markov decision processes: an empirical process theory approach
• Risk sensitive control and large deviations for denumerable Markov decision processes
• Large deviations and optimal control for Markov decision processes

This page was built for publication: Rate of Convergence of Empirical Measures and Costs in Controlled Markov Chains and Transient Optimality

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4698108)