Analysis of an Adaptive Control Scheme for a Partially Observed Controlled Markov Chain

Abstract

The authors consider an adaptive finite state-controlled Markov chain with partial state information, motivated by a class of replacement problems. They present parameter estimation techniques based on the information available after actions that reset the state to a known value are taken. They prove that the parameter estimates converge w.p.1 to the true (unknown) parameter, under the feedback structure induced by a certainty equivalent adaptive policy. They also show that the adaptive policy is self-optimizing, in a long-run average sense, for any (measurable) sequence of parameter estimates converging w.p.1 to the true parameter.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Dec 01, 1991
Accession Number
ADA454807

Entities

People

  • Aristotle Arapostathis
  • Emmanuel Fernandez-gaucherand
  • Steven I Marcus

Organizations

  • University of Maryland

Tags

DTIC Thesaurus Topics

  • Abstracts
  • Electrical Engineering
  • Engineering
  • Industrial Engineering
  • Information Operations
  • Markov Chains
  • Maryland
  • Mathematics
  • Systems Engineering
  • Universities

Fields of Study

  • Mathematics

Readers

  • Mathematical Modeling and Probability Theory.
  • Regression Analysis.
  • Robotics and Automation.