Average cost Markov control processes with weighted norms: value iteration

DOI10.4064/am-23-2-219-237zbMath0829.93068MaRDI QIDQ4848289

Onésimo Hernández-Lerma, Evgueni I. Gordienko

Publication date: 24 January 1996

Published in: Applicationes Mathematicae (Search for Journal in Brave)

Full work available at URL: https://eudml.org/doc/219127

zbMATH Keywords

convergence; value iteration; Markov control processes; average cost optimality

Mathematics Subject Classification ID

93E20: Optimal stochastic control

90C40: Markov and semi-Markov decision processes

Related Items

Unnamed Item, Asymptotic Normality of Discrete-Time Markov Control Processes, Unnamed Item, Unnamed Item, Weakly coupled event triggered output feedback system in wireless networked control systems, On the optimality equation for average cost Markov control processes with Feller transition probabilities, Discounted cost optimality problem: Stability with respect to weak metrics, Robustness inequality for Markov control processes with unbounded costs, Approximation of average cost optimal policies for general Markov decision processes with unbounded costs, ``Super-overtaking optimal policies for Markov control processes, Semi-Markov control processes with unknown holding times distribution under an average cost criterion, Redundant data transmission in control/estimation over lossy networks, Empirical estimation in average Markov control processes, Another set of conditions for Markov decision processes with average sample-path costs, Unnamed Item, Bayesian estimation of the mean holding time in average semi-Markov control processes