On functional equations for Kth best policies in Markov decision processes

DOI10.1016/J.AUTOMATICA.2012.09.016MaRDI QIDQ1939643zbMATH OpenOpenAlexFDO

Authors Hyeong Soo Chang

Publication date 4 March 2013

Published in Automatica (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/j.automatica.2012.09.016

zbMATH Keywords

ranksdynamic programmingMarkov decision processescorrected Bellman and Kalaba's equations

Mathematics Subject Classification ID

Analysis of variance and covariance (ANOVA) (62J10) Optimal stochastic control (93E20)

Recommendations

• scientific article; zbMATH DE number 700091
• Existence theorems of solutions for certain classes of functional equations arising in dynamic programming
• scientific article; zbMATH DE number 4154239
• On Markovian decision programming with recursive reward functions
• Ranking policies in discrete Markov decision processes

Cited in

(5)

• Ordinary differential equation methods for Markov decision processes and application to Kullback-Leibler control cost
• Finding Best k Policies
• Neuro-optimal tracking control for a class of discrete-time nonlinear systems via generalized value iteration adaptive dynamic programming approach
• A functional equation arising in multi-agent statistical decision theory
• Relevant states and memory in Markov chain bootstrapping and simulation

This page was built for publication: On functional equations for \(K\)th best policies in Markov decision processes

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1939643)