Value iteration in a class of average controlled Markov chains with unbounded costs: necessary and sufficient conditions for pointwise convergence

DOI10.2307/3214980zbMATH Open0869.93054OpenAlexW4255849103MaRDI QIDQ3122864FDOQ3122864

Authors Rolando Cavazos-Cadena, Emmanuel Fernández-Gaucherand 

Publication date 5 March 1997

Published in Journal of Applied Probability (Search for Journal in Brave)

Full work available at URL https://doi.org/10.2307/3214980

zbMATH Keywords

Lyapunov conditionnecessary and sufficient optimality conditionsaverage costcontrolled Markov chain

Mathematics Subject Classification ID

Markov and semi-Markov decision processes (90C40) Optimal stochastic control (93E20)

Recommendations

• scientific article; zbMATH DE number 970660
• Value iteration in countable state average cost Markov decision processes with unbounded costs
• The convergence of value iteration in average cost Markov decision chains
• A note on the convergence rate of the value iteration scheme in controlled Markov chains

Cited in

(8)

• On convergence of value iteration for a class of total cost Markov decision processes
• Average cost Markov control processes with weighted norms: value iteration
• STRONG AVERAGE OPTIMALITY FOR CONTROLLED NONHOMOGENEOUS MARKOV CHAINS^*
• A note on the convergence rate of the value iteration scheme in controlled Markov chains
• A pause control approach to the value iteration scheme in average Markov decision processes
• Continuous-time controlled Markov chains.
• Approximation of average cost optimal policies for general Markov decision processes with unbounded costs
• Time-average optimal constrained semi-Markov decision processes

This page was built for publication: Value iteration in a class of average controlled Markov chains with unbounded costs: necessary and sufficient conditions for pointwise convergence

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3122864)