Multiaction learning automata possessing ergodicity of the mean

DOI10.1016/0020-0255(85)90049-0zbMath0581.68047OpenAlexW1967960734WikidataQ60328382 ScholiaQ60328382MaRDI QIDQ1067787

M. A. L. Thathachar, B. John Oommen

Publication date: 1985

Published in: Information Sciences (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/0020-0255(85)90049-0

zbMATH Keywords

linear dependenceergodic Markov chainmean action probabilityprobability updating functions

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Multi-automaton games: a rationale for expedient collective behavior
• Automaton theory and modelling of biological systems. Translated by Scitran (Scientific Translation Service)
• Use of learning automata for the control of random search
• Some convergence theorems for stochastic learning models with distance diminishing operators
• Markov processes and learning models
• On the behavior of stochastic automata with a variable structure
• Learning automata processing ergodicity of the mean: The two-action case
• Gradient approach for recursive estimation and control in finite Markov chains
• Learning Automata - A Survey
• Absolutely Expedient Learning Algorithms for Stochastic Automata

This page was built for publication: Multiaction learning automata possessing ergodicity of the mean