Adaptive stepsizes for recursive estimation with applications in approximate dynamic programming

DOI10.1007/s10994-006-8365-9zbMath1475.90122MaRDI QIDQ851872

Warren B. Powell, Abraham P. George

Publication date: 22 November 2006

Published in: Machine Learning (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/s10994-006-8365-9

zbMATH Keywords

adaptive learning; Kalman filter; approximate dynamic programming; stochastic stepsize

Mathematics Subject Classification ID

90C39: Dynamic programming

Related Items

Minimizing total tardiness in a stochastic single machine scheduling problem using approximate dynamic programming

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Forecasting Sales by Exponentially Weighted Moving Averages
• Exponentiated gradient versus gradient descent for linear predictors
• Recursive estimation and time-series analysis. An introduction
• Accelerated Stochastic Approximation
• On the identification of non-stationary linear processes
• A method of aggregate stochastic subgradients with on-line stepsize rules for convex stochastic programming problems
• A stochastic gradient adaptive filter with gradient adaptive step size
• Introduction to Stochastic Search and Optimization
• Analysis of adaptive step-size SA algorithms for parameter tracking
• Learning Applied to Successive Approximation Algorithms
• Stochastic Estimation of the Maximum of a Regression Function
• A Stochastic Approximation Method
• Approximation Methods which Converge with Probability one
• Multidimensional Stochastic Approximation Methods
• Adaptive filtering
• The elements of statistical learning. Data mining, inference, and prediction