Recursive Algorithms for Adaptive Control of Finite Markov Chains

DOI10.1109/TSMC.1981.4308638zbMath0474.93078OpenAlexW2013009405MaRDI QIDQ3931288

Yousri M. Abd-El-Fattah

Publication date: 1981

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.1981.4308638

zbMATH Keywords

parameter estimationlearning automataadaptationrecursive algorithmscontrolled Markov chainspolicy variationsTaylor-like expansion formula of the expected average reward

Mathematics Subject Classification ID

Discrete-time Markov processes on general state spaces (60J05) Adaptive control/observation systems (93C40) Estimation and detection in stochastic control theory (93E10) Series expansions (e.g., Taylor, Lidstone series, but not Fourier series) (41A58)

Related Items (2)

Parameter estimation in stochastic systems: some recent results and applications ⋮ Tool replacement with adaptive control in a non-stationary non-periodic stochastic process

This page was built for publication: Recursive Algorithms for Adaptive Control of Finite Markov Chains