Solving linear quadratic discrete-time optimal controls using neural networks
- 1 January 1990
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 2770-2772 vol.5
- https://doi.org/10.1109/cdc.1990.203282
Abstract
The authors describe a unique implementation of linear quadratic (LQ) optimal control using the Hopfield type of neural network. They discuss the neural network architecture for LQ optimal control and present simulation results. They also discuss its extension to the solution of linear quadratic Gaussian optimal control problems.Keywords
This publication has 5 references indexed in Scilit:
- Identification and control of dynamical systems using neural networksIEEE Transactions on Neural Networks, 1990
- Adaptive Control of Unknown Dynamical Systems via Neural Network ApproachPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1989
- Simple 'neural' optimization networks: An A/D converter, signal decision circuit, and a linear programming circuitIEEE Transactions on Circuits and Systems, 1986
- Parallel Distributed ProcessingPublished by MIT Press ,1986
- “Neural” computation of decisions in optimization problemsBiological Cybernetics, 1985