Optimizing Simulations with Noise-Tolerant Structured Exploration

ICRA, pp. 2970-2977, 2018.

Cited by: 4|Bibtex|Views71|DOI:https://doi.org/10.1109/icra.2018.8460492
EI
Other Links: dblp.uni-trier.de|academic.microsoft.com|arxiv.org

Abstract:

We propose a simple drop-in noise-tolerant replacement for the standard finite difference procedure used ubiquitously in blackbox optimization. In our approach, parameter perturbation directions are defined by a family of structured orthogonal matrices. We show that at the small cost of computing a Fast Walsh-Hadamard/Fourier Transform (F...More

Code:

Data:

Your rating :
0

 

Tags
Comments