Recursive self-tuning control of finite Markov chains

DOI10.4064/AM-24-2-169-188MaRDI QIDQ3122806zbMATH OpenOpenAlexFDO

Authors Vivek Borkar

Publication date 3 January 2001

Published in Applicationes Mathematicae (Search for Journal in Brave)

Full work available at URL https://eudml.org/doc/219177

zbMATH Keywords

adaptive controlfinite Markov chainsrelative value iterationrecursive self-tuning control schemestochastic approximation scheme

Mathematics Subject Classification ID

Stochastic learning and adaptive control (93E35)

Recommendations

• Ergodic and adaptive control of nearest-neighbor motions
• scientific article; zbMATH DE number 3924660
• Learning control of finite Markov chains with an explicit trade-off between estimation and control
• On the Milito-Cruz adaptive control scheme for Markov chains

Cited in

(6)

• scientific article; zbMATH DE number 409876 (Why is no real title available?)
• Ergodic and adaptive control of nearest-neighbor motions
• Stochastic approximation algorithms: overview and recent trends.
• The Kumar-Becker-Lin scheme revisited
• Adaptive service rate control of an M/M/1 queue with server breakdowns
• Sample complexity for Markov chain self-tuner

This page was built for publication: Recursive self-tuning control of finite Markov chains

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3122806)