The Kumar-Becker-Lin scheme revisited

DOI10.1007/BF00939540zbMath0682.93060OpenAlexW2045812400MaRDI QIDQ1824599

Vivek S. Borkar

Publication date: 1990

Published in: Journal of Optimization Theory and Applications (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/bf00939540

zbMATH Keywords

parameter estimationMarkov chainsergodic controlKumar-Becker-Lin schemea.s. optimalityself- tuning control

Mathematics Subject Classification ID

Adaptive control/observation systems (93C40) Estimation and detection in stochastic control theory (93E10) Markov chains (discrete-time Markov processes on discrete state spaces) (60J10) Optimal stochastic control (93E20)

Related Items (5)

On nearly self-optimizing strategies for a discrete-time uniformly ergodic adaptive model ⋮ Self-tuning control of diffusions without the identifiability condition ⋮ Ergodic and adaptive control of nearest-neighbor motions ⋮ Multiscale Stochastic Approximation for Parametric Optimization of Hidden Markov Models ⋮ On the Milito-Cruz adaptive control scheme for Markov chains

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• A convex analytic approach to Markov decision processes
• Ergodic and adaptive control of nearest-neighbor motions
• Adaptive control of Markov chains, I: Finite parameter set
• A Survey of Some Results in Stochastic Adaptive Control
• Estimation and control in discounted stochastic dynamic programming
• Control of Markov Chains with Long-Run Average Cost Criterion: The Dynamic Programming Equations
• A new family of optimal adaptive controllers for Markov chains
• Optimal adaptive controllers for unknown Markov chains
• Identification and Adaptive Control of Markov Chains
• Hitting-time and occupation-time bounds implied by drift analysis with applications
• Parameter estimation in continuous-time stochastic processes
• Estimation and control in Markov chains
• Existence of Optimal Strategies Based on Specified Information, for a Class of Stochastic Decision Problems

This page was built for publication: The Kumar-Becker-Lin scheme revisited