On ordinal comparison of policies in Markov reward processes

DOI10.1023/B:JOTA.0000041736.82051.F1MaRDI QIDQ852153zbMATH OpenFDO

Authors N. E. Zubov

Publication date 27 November 2006

Published in Journal of Optimization Theory and Applications (Search for Journal in Brave)

zbMATH Keywords

large deviationsstochastic simulationsMarkov reward processesordinal comparisons

Mathematics Subject Classification ID

Large deviations (60F10) Discrete event control/observation systems (93C65) Stochastic stability in control theory (93E15) Optimal stochastic control (93E20)

Recommendations

• Comparing Policies in Markov Decision Processes: Mandl's Lemma Revisited
• Ranking policies in discrete Markov decision processes
• Ordinal decision models for Markov decision processes
• Computational comparison of policy iteration algorithms for discounted Markov decision processes
• A preorder relation for Markov reward processes
• A note on policy algorithms for discounted Markov decision problems
• On Markov policies for minimax decision processes
• Stochastic comparison of discounted rewards
• Ordinal Bayesian incentive compatibility in restricted domains

Cites work

• scientific article; zbMATH DE number 700091 (Why is no real title available?)
• Adaptive Markov control processes
• Convergence of stochastic processes
• Convergence properties of ordinal comparison in the simulation of discrete event dynamic systems
• Hoeffding's inequality for uniformly ergodic Markov chains
• Markov chains and stochastic stability
• On the convergence rate of ordinal comparisons of random variables
• Ordinal optimisation and simulation

Cited in

(1)

• On convergence rate of the Shannon entropy rate of ergodic Markov chains via sample-path simulation

This page was built for publication: On ordinal comparison of policies in Markov reward processes

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q852153)