Stochastic Recursive Algorithms for Optimization Simultaneous Perturbation Methods /

Stochastic Recursive Algorithms for Optimization presents algorithms for constrained and unconstrained optimization and for reinforcement learning. Efficient perturbation approaches form a thread unifying all the algorithms considered. Simultaneous perturbation stochastic approximation and smooth fr...

Full description

Bibliographic Details
Main Authors: Bhatnagar, S. (Author), Prasad, H.L. (Author), Prashanth, L.A. (Author)
Corporate Author: SpringerLink (Online service)
Format: Electronic
Language:English
Published: London : Springer London : Imprint: Springer, 2013.
Series:Lecture Notes in Control and Information Sciences, 434
Subjects:
Online Access:https://ezaccess.library.uitm.edu.my/login?url=http://dx.doi.org/10.1007/978-1-4471-4285-0
Table of Contents:
  • Part I: Introduction to Stochastic Recursive Algorithms
  • Introduction
  • Deterministic Algorithms for Local Search
  • Stochastic Approximation Algorithms
  • Part II: Gradient Estimation Schemes
  • Kiefer-Wolfowitz Algorithm
  • Gradient Schemes with Simultaneous Perturbation Stochastic Approximation
  • Smoothed Functional Gradient Schemes
  • Part III: Hessian Estimation Schemes
  • Hessian Estimation with Simultaneous Perturbation Stochasti Approximation
  • Smoothed Functional Hessian Schemes
  • Part IV: Variations to the Basic Scheme
  • Discrete Optimization
  • Algorithms for Contrained Optimization
  • Reinforcement Learning
  • Part V: Applications
  • Service Systems
  • Road Traffic Control
  • Communication Networks.