Gradient approach for recursive estimation and control in finite Markov chains

DOI10.2307/1426973zbMath0475.60051OpenAlexW2143116909MaRDI QIDQ3930407

Yousri M. Abd-El-Fattah

Publication date: 1981

Published in: Advances in Applied Probability (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.2307/1426973

zbMATH Keywords

parameter estimationlearning automataadaptationrecursive algorithmscontrolled Markov chains

Mathematics Subject Classification ID

Markov processes: estimation; hidden Markov models (62M05) Markov chains (discrete-time Markov processes on discrete state spaces) (60J10) Markov and semi-Markov decision processes (90C40)

Related Items (4)

Multi-automaton games: a rationale for expedient collective behavior ⋮ Stochastic approximation algorithms: overview and recent trends. ⋮ Analysis of an identification algorithm arising in the adaptive estimation of Markov chains ⋮ Multiaction learning automata possessing ergodicity of the mean

This page was built for publication: Gradient approach for recursive estimation and control in finite Markov chains