Asymptotically Efficient Adaptive Choice of Control Laws inControlled Markov Chains

DOI10.1137/S0363012994275440MaRDI QIDQ4337732zbMATH OpenOpenAlexFDO

Authors Tze Leung Lai, Todd L. Graves

Publication date 26 May 1997

Published in SIAM Journal on Control and Optimization (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1137/s0363012994275440

zbMATH Keywords

certainty equivalencesequential testingadaptive control of Markov chainsmultiarmed bandit problemuncertainty adjustments

Mathematics Subject Classification ID

Applications of Markov chains and discrete-time Markov processes on general state spaces (social mobility, learning theory, industrial processes, etc.) (60J20) Sequential statistical analysis (62L10) Adaptive control/observation systems (93C40) Optimal stochastic control (93E20) Stochastic learning and adaptive control (93E35)

Recommendations

• An optimization-oriented approach to the adaptive control of Markov chains
• scientific article; zbMATH DE number 3849083
• Adaptive control of constrained Markov chains: Criteria and policies
• Adaptive control of constrained Markov chains
• scientific article; zbMATH DE number 4042964
• Adaptive control of constrained finite Markov chains
• scientific article; zbMATH DE number 440539
• On adaptive control of a partially observed Markov chain

Cited in

(19)

• Minimizing the learning loss in adaptive control of Markov chains under the weak accessibility condition
• Adaptive control design under structured model information limitation: a cost-biased maximum-likelihood approach
• Learning the distribution with largest mean: two bandit frameworks
• Adaptive policies for perimeter surveillance problems
• scientific article; zbMATH DE number 4123661 (Why is no real title available?)
• Learning to optimize via information-directed sampling
• scientific article; zbMATH DE number 3849083 (Why is no real title available?)
• Asymptotically efficient adaptive allocation schemes for controlled Markov chains: finite parameter space
• scientific article; zbMATH DE number 4109753 (Why is no real title available?)
• The Sufficiency of Adjoined Markov Strategies for Controlled Diffusion Processes
• scientific article; zbMATH DE number 3847250 (Why is no real title available?)
• Adaptive control of a Markov chain over a finite parameter set without continuity assumptions on the control laws
• Asymptotically efficient adaptive allocation schemes for controlled i.i.d. processes: finite parameter space
• Sequential Generalized Likelihood Ratios and Adaptive Treatment Allocation for Optimal Sequential Selection
• Adaptive control of Markov chains with average cost
• An asymptotically optimal learning controller for finite Markov chains with unknown transition probabilities
• Assessing the Impact of Head Starts in the Performance of One-Sided Markov-Type Control Schemes
• Optimal strategies for a class of sequential control problems with precedence relations
• The multi-armed bandit problem: an efficient nonparametric solution

This page was built for publication: Asymptotically Efficient Adaptive Choice of Control Laws inControlled Markov Chains

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4337732)