Performance of evolutionary wavelet neural networks in acrobot control tasks

Title: Performance of evolutionary wavelet neural networks in acrobot control tasks
Creator: Khan, Maryam Mahsal; Mendes, Alexandre; Chalup, Stephan K.
Relation: Neural Computing and Applications Vol. 32, Issue 12, p. 8493-8505
Publisher Link: http://dx.doi.org/10.1007/s00521-019-04347-x
Publisher: Springer
Resource Type: journal article
Date: 2020
Description: Wavelet neural networks (WNN) combine the strength of artificial neural networks and the multiresolution ability of wavelets. Determining the structure and, more specifically, the appropriate number of neurons in a WNN is a time-consuming process. We propose a type of multidimensional evolutionary WNN and, using an acrobot, evaluate this approach with two benchmark nonlinear control tasks: a height task and a hand-stand task. To facilitate direct comparison with other methods, we report on swing-up and balance times. In 50 trials, the controllers produced faster swing-up times-1.0 s for the best controller and 2.3 s on average-than any other methods reported in the literature. Moreover, the controller with the best swing-up time had a maximum balance time of 1.25 s, surpassing most other methods.
Subject: evolutionary algorithms; wavelet neural networks; acrobot; intelligent control
Identifier: http://hdl.handle.net/1959.13/1462084
Identifier: uon:46386
Identifier: ISSN:0941-0643
Language: eng
Reviewed

		Thumbnail	File	Description	Size	Format