Approximating optimal state feedback using neural networks

Approximating optimal state feedback using neural networks

Caption title.

Bibliographic Details
Other Authors:	McDermott, Wesley.
Language:	eng
Published:	Massachusetts Institute of Technology, Laboratory for Information and Decision Systems] 2003
Subjects:	TK7855.M41 E3845 no.2249
Online Access:	http://hdl.handle.net/1721.1/3373

Similar Items

State feedback l1-optimal controller can be dynamic
Published: (2003)

Asynchronous stochastic approximation and Q-learning
Published: (2003)

Optimal stopping of Markov processes : Hilbert space theory, approximation algorithms, and an application to pricing high-dimensional financial derivatives
Published: (2003)

Stable teleoperation with scaled feedback
Published: (2003)

An analysis of temporal-difference learning with function approximation
Published: (2003)

Feedback system design with an uncertain plant
Published: (2003)

Point estimation, stochastic approximation, and robust Kalman filtering
Published: (2003)

Parallel computing in network optimization
Published: (2003)

Pade' approximants to matrix Stieltjes series : convergence and related properties
Published: (2003)

Some discrete approximations to a variational method for image segmentation
Published: (2002)

A Method for designing robust multivariable feedback systems
Published: (2003)

A method for designing robust multivariable feedback systems
Published: (2003)

A note on the greedy approximation algorithm for the unweighted set covering problem
Published: (2003)

The complexity of optimal queueing network control
Published: (2003)

Optimal control of noisy finite-state Markov processes
Published: (2002)

Design of feedback control systems for stable plants with saturating actuators
Published: (2003)

Design of feedback control systems for unstable plants with saturating actuators
Published: (2003)

Design of feedback control systems for stable plants with saturating actuators
Published: (2003)

Zero error decision feedback capacity of discrete memoryless channels
Published: (2003)

A functional expansion approach to the solution of nonlinear feedback systems
Published: (2002)

Spectral quantities associated to pairs of matrices are hard, when not impossible, to compute and to approximate
Published: (2003)

Stable linear approximations to dynamic programming for stochastic control problems with local transitions
Published: (2003)

An existence theorem and lattice approximations for a variational problem arising in computer vision
Published: (2003)

Lattice approximation in the stochastic quantization of ([phi]4Ì³)2Ì³fields
Published: (2003)

An optimal multigrid algorithm for continuous state discrete time stochastic control
Published: (2003)

A decomposition method for the approximate evaluation of capacitated transfer line with unreliable machines and random processing times
Published: (2003)

Optimization of multiclass queueing networks : polyhedral and nonlinear characterization of achievable performance
Published: (2003)

On feedback laws for robotic systems
Published: (2002)

A hierarchicial algorithm for neural training and control
Published: (2003)

Autonomy and adaptiveness : a perspective on integrative neural architectures
Published: (2003)

Multiscale object recognition and feature extraction using wavelet networks (U)
Published: (2003)

Intelligent optimal control
Published: (2003)

Optimal communication algorithms for hypercubes
Published: (2003)

Rollout algorithms for combinatorial optimization
Published: (2003)

Communication complexity of convex optimization
Published: (2003)

On the distributions of optimized multiscale representations
Published: (2003)

Basis descent methods for convex essentially smooth optimization with applications to quadratic/entropy optimization and resource allocation
Published: (2003)

Efficient algorithms for globally optimal trajectories
Published: (2003)

Optimal robust H-[infinity] control
Published: (2003)

Optimal recursive maximum likelihood estimation
Published: (2003)