Learning automata processing ergodicity of the mean: The two-action case

DOI10.1109/TSMC.1983.6313191MaRDI QIDQ3323275zbMATH OpenOpenAlexWikidataFDO

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

Publication date 1983

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.1983.6313191

zbMATH Keywords

action probabilityergodicity of the meanLearning automatalinear algorithmnonlinear updating schemesrate of convergencetwo-action case

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Recommendations

• Multiaction learning automata possessing ergodicity of the mean
• Absorbing and Ergodic Discretized Two-Action Learning Automata
• epsilon -optimal discretized linear reward-penalty learning automata
• The asymptotic optimality of discretized linear reward-inaction learning automata
• scientific article; zbMATH DE number 4131679

Cited in

(6)

• Multiaction learning automata possessing ergodicity of the mean
• Absorbing and Ergodic Discretized Two-Action Learning Automata
• History dependent stochastic automata: A formal view of evolutionary learning
• epsilon -optimal discretized linear reward-penalty learning automata
• scientific article; zbMATH DE number 1189122 (Why is no real title available?)
• Learning action probabilities from delayed reinforcement

This page was built for publication: Learning automata processing ergodicity of the mean: The two-action case

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3323275)