DocumentCode :
324526
Title :
Application considerations for the DHP methodology
Author :
Lendaris, George G. ; Shannon, Thaddeus
Author_Institution :
Dept. of Syst. Sci. & Electr. Eng., Portland State Univ., OR, USA
Volume :
2
fYear :
1998
fDate :
4-9 May 1998
Firstpage :
1013
Abstract :
Six questions are posed that are likely to be of interest to one considering applying the dual heuristic programming (DHP) methodology. Tentative answers to these questions are provided in the last section of the paper. As a basis for these, the paper first describes observations made from a series of explorations into various aspects of using the DHP method to design the controller for the pole-cart benchmark problem. Parameters of the explorations included training gains, plant parameter variations, fidelity of plant model, controller sampling rates, network architectures, training strategies, and generalization tests
Keywords :
control system synthesis; generalisation (artificial intelligence); heuristic programming; learning (artificial intelligence); neural net architecture; neurocontrollers; DHP methodology; controller sampling rates; dual heuristic programming methodology; fidelity; generalization tests; network architectures; plant model; plant parameter variations; pole-cart benchmark problem; training gains; training strategies; Analytical models; Benchmark testing; Design methodology; Design optimization; Equations; Mathematical programming; Neural networks; Process design; Sampling methods; Signal generators;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Neural Networks Proceedings, 1998. IEEE World Congress on Computational Intelligence. The 1998 IEEE International Joint Conference on
Conference_Location :
Anchorage, AK
ISSN :
1098-7576
Print_ISBN :
0-7803-4859-1
Type :
conf
DOI :
10.1109/IJCNN.1998.685910
Filename :
685910
Link To Document :
بازگشت