Nonlinear ergodic \(\varepsilon{}\)-optimal discretized reward-penalty learning automata and their application to adaptive routing algorithms

DOI10.1016/0925-2312(91)90032-7zbMath0800.68696OpenAlexW2066714957MaRDI QIDQ1180034

Publication date: 27 June 1992

Published in: Neurocomputing (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/0925-2312(91)90032-7

zbMATH Keywords

ergodic learning automaton exponentially discretized reward-penalty learning automaton nonlinear learning automaton

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

This page was built for publication: Nonlinear ergodic \(\varepsilon{}\)-optimal discretized reward-penalty learning automata and their application to adaptive routing algorithms