Absorbing and Ergodic Discretized Two-Action Learning Automata

DOI10.1109/TSMC.1986.4308951MaRDI QIDQ3746893zbMATH OpenWikidataFDO

Authors B. John Oommen

Publication date 1986

Published in IEEE Transactions on Systems, Man, and Cybernetics (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1109/TSMC.1986.4308951

zbMATH Keywords

discretized automatonMarkovian representationrandom environmentsvariable-structure stochastic automata

Mathematics Subject Classification ID

Formal languages and automata (68Q45) Learning and adaptive systems in artificial intelligence (68T05)

Recommendations

• epsilon -optimal discretized linear reward-penalty learning automata
• The asymptotic optimality of discretized linear reward-inaction learning automata
• Multiaction learning automata possessing ergodicity of the mean
• Discretized pursuit learning automata
• Learning automata processing ergodicity of the mean: The two-action case

Cited in

(20)

• Asymptotic behavior of a hierarchical system of learning automata
• Multiaction learning automata possessing ergodicity of the mean
• Absorbing stochastic estimator learning automata for S-model stationary environments
• A novel technique for stochastic root-finding: enhancing the search with adaptive d-ary search
• The design of absorbing Bayesian pursuit algorithms and the formal analyses of their \(\varepsilon\)-optimality
• Stochastic learning-based weak estimation of multinomial random variables and its applications to pattern recognition in non-stationary environments
• Stochastic discretized learning-based weak estimation: a novel estimation method for non-stationary environments
• scientific article; zbMATH DE number 4131679 (Why is no real title available?)
• On the analysis of a random interleaving walk-jump process with applications to testing
• The asymptotic optimality of discretized linear reward-inaction learning automata
• Asymptotic behaviour of a learning algorithm
• Learning automata processing ergodicity of the mean: The two-action case
• scientific article; zbMATH DE number 3864534 (Why is no real title available?)
• scientific article; zbMATH DE number 3874622 (Why is no real title available?)
• Discretized pursuit learning automata
• scientific article; zbMATH DE number 3980494 (Why is no real title available?)
• epsilon -optimal discretized linear reward-penalty learning automata
• Learning action probabilities from delayed reinforcement
• On the analysis of a random walk-jump chain with tree-based transitions and its applications to faulty dichotomous search
• Pioneering approaches for enhancing the speed of hierarchical LA by \textit{ordering} the actions

This page was built for publication: Absorbing and Ergodic Discretized Two-Action Learning Automata

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3746893)