An asynchronous stochastic approximation theorem and some applications

MaRDI QIDQ2707252zbMATH OpenFDO

Authors Csaba Szepesvári

Publication date 1 April 2001

Published in Alkalmazott Matematikai Lapok. A Magyar Tudomanyos Akademia. Matematikai es Fizikai Tudomanyok Osztalyanak Közlemenyei (Search for Journal in Brave)

zbMATH Keywords

Markov decision problems

Mathematics Subject Classification ID

Markov and semi-Markov decision processes (90C40) Optimal stochastic control (93E20)

Recommendations

• The Borkar-Meyn theorem for asynchronous stochastic approximations
• scientific article; zbMATH DE number 4123661
• Asynchronous stochastic approximation with differential inclusions
• Asynchronous stochastic approximation and Q-learning
• scientific article; zbMATH DE number 4045510

Cited in

(1)

• Asymptotic agreement and convergence of asynchronous stochastic algorithms

This page was built for publication: An asynchronous stochastic approximation theorem and some applications

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2707252)