Can we cope with the curse of dimensionality in optimal control by using neural approximators?

Proceedings of the IEEE Conference on Decision and Control

Volumn 4, Issue , 2001, Pages 3540-3545

  Zoppoli, R ^a   Sanguineti, M ^a   Parisini, T ^a  

^a UNIVERSITY OF GENOA   (Italy)

Author keywords

[No Author keywords available]

Indexed keywords

APPROXIMATION THEORY; FUNCTIONS; NEURAL NETWORKS; NONLINEAR CONTROL SYSTEMS; OPTIMIZATION; PROBABILITY DENSITY FUNCTION; PROBLEM SOLVING; VECTORS;

DIMENSIONALITY; EXTENDED RITZ METHOD; NEURAL APPROXIMATORS;

OPTIMAL CONTROL SYSTEMS;

EID: 0035713285     PISSN: 01912216     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (14)

1. Computational methods for parametric LQ problems- A survey
2. Neural approximations for multistage optimal control of nonlinear stochastic systems
3. A neural state estimator with bounded errors for nonlinear systems
4. Approximating networks and extended Ritz method for the solution of functional optimization problems
5. Successive Galerkin approximation algorithms for nonlinear optimal and robust control
6. Multilayer feedforward networks with a nonpolynomial activation function can approximate any function
7. Bounds on rates of variable-basis and neural-network approximation
8. Comparison of worst-case errors in linear and neural network approximation
9. Universal approximation bounds for superpositions of a sigmoidal function
10. Motorway network control via nonlinear optimization