Document Type
Pre-Print
Publication Date
12-1-1999
Abstract
A variety of alternate training strategies for implementing the Dual Heuristic Programming (DHP) method of approximate dynamic programming in the neuro-control context are explored. The DHP method of controller training has been successfully demonstrated by a number of authors on a variety of control problems in recent years, but no unified view of the implementation details of the method has yet emerged. A number of options are here described for sequencing the training of the Controller and Critic networks in DHP implementations. Results are given about their relative efficiency and the quality of the resulting controllers for two benchmark control problems.
Rights
Proceedings of the International Joint Conference on Neural Networks
Persistent Identifier
https://archives.pdx.edu/ds/psu/37276
Citation Details
Lendaris, George G.; Shannon, Thaddeus T.; and Rustan, Andres, "A Comparison of Training Algorithms for DHP Adaptive Critic Neuro-Control" (1999). Systems Science Faculty Publications and Presentations. 199.
https://archives.pdx.edu/ds/psu/37276