Ergodic control of multidimensional diffusions. II: Adaptive control

DOI10.1007/BF01445163zbMATH Open0691.93027OpenAlexW1994625434MaRDI QIDQ583162FDOQ583162

Mrinal K. Ghosh, Vivek Borkar

Publication date: 1990

Published in: Applied Mathematics and Optimization (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/bf01445163

Recommendations

• Self-tuning control of diffusions without the identifiability condition
• Almost self-optimizing strategies for the adaptive control of diffusion processes
• Bayesian ergodic adaptive control of diffusion processes
• Ergodic Control of Multidimensional Diffusions I: The Existence Results
• scientific article; zbMATH DE number 778102

zbMATH Keywords

maximum likelihood estimationadaptive controldiffusion processlong-run average cost criterionAsymptotic optimalityself-tuning scheme

Mathematics Subject Classification ID

Diffusion processes (60J60) Existence of optimal solutions to problems involving randomness (49J55) Adaptive control/observation systems (93C40) Optimal stochastic control (93E20)

Cites Work

• On self tuning regulators
• On the Hamilton-Jacobi-Bellman equations
• Title not available (Why is that?)
• Title not available (Why is that?)
• A topology for Markov controls
• Bounds for the fundamental solution of a parabolic equation
• Ergodic Properties of Recurrent Diffusion Processes and Stabilization of the Solution to the Cauchy Problem for Parabolic Equations
• ON STRONG SOLUTIONS AND EXPLICIT FORMULAS FOR SOLUTIONS OF STOCHASTIC INTEGRAL EQUATIONS
• Title not available (Why is that?)
• A Survey of Some Results in Stochastic Adaptive Control
• Existence of Optimal Strategies Based on Specified Information, for a Class of Stochastic Decision Problems
• SOME NEW RESULTS IN THE THEORY OF CONTROLLED DIFFUSION PROCESSES
• Ergodic Control of Multidimensional Diffusions I: The Existence Results
• Estimation and control in Markov chains
• Existence results for optimal stochastic controls
• Estimation and control in discounted stochastic dynamic programming
• Optimal adaptive controllers for unknown Markov chains
• Identification and Adaptive Control of Markov Chains
• Parameter estimation in continuous-time stochastic processes

Cited In (18)

• Title not available (Why is that?)
• Bias and overtaking equilibria for zero-sum stochastic differential games
• Characterizations of overtaking optimality for controlled diffusion processes
• Parameter estimation for controlled semilinear stochastic systems: Identifiability and consistency
• Blackwell Optimality for Controlled Diffusion Processes
• A strong approximation theorem for stochastic recursive algorithms
• The value function in ergodic control of diffusion processes with partial observations II
• Controlled diffusions with constraints
• Optimal control of molecular dynamics using Markov state models
• On the ergodic and the adaptive control of stochastic differential delay systems
• Self-tuning control of diffusions without the identifiability condition
• Adaptive control of diffusion processes with a discounted reward criterion
• Policy iteration algorithms for zero-sum stochastic differential games with long-run average payoff criteria
• Ergodic Control, Bias, and Sensitive Discount Optimality for Markov Diffusion Processes
• Title not available (Why is that?)
• Ergodic Control of Multidimensional Diffusions I: The Existence Results
• A note on controlled diffusions with long finite horizon
• Continuity of cost in Borkar control topology and implications on discrete space and time approximations for controlled diffusions under several criteria

This page was built for publication: Ergodic control of multidimensional diffusions. II: Adaptive control

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q583162)