Two ε-Optimal Nonlinear Reinforcement Schemes for Stochastic Automata

DOI10.1109/TSMC.1974.5408538MaRDI QIDQ4401894zbMATH OpenFDO

Authors Yoshikazu Sawaragi, Norio Baba

Publication date 1974

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

Mathematics Subject Classification ID

Formal languages and automata (68Q45)

Cited in

(5)

• Learning behavior of stochastic automata in the last stage of learning
• Theoretical considerations of the parameter self-optimization by stochastic automata
• epsilon-optimality of a general class of learning algorithms
• scientific article; zbMATH DE number 3780600 (Why is no real title available?)
• Probabilistic automata

This page was built for publication: Two ε-Optimal Nonlinear Reinforcement Schemes for Stochastic Automata

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4401894)