Efficient natural evolution strategies

Yi Sun, Daan Wierstra, Tom Schaul, Juergen Schmidhuber

Research output: Chapter in Book/Report/Conference proceedingConference contribution

65 Scopus citations

Abstract

Efficient Natural Evolution Strategies (eNES) is a novel alternative to conventional evolutionary algorithms, using the natural gradient to adapt the mutation distribution. Unlike previous methods based on natural gradients, eNES uses a fast algorithm to calculate the inverse of the exact Fisher information matrix, thus increasing both robustness and performance of its evolution gradient estimation, even in higher dimensions. Additional novel aspects of eNES include optimal fitness baselines and importance mixing (a procedure for updating the population with very few fitness evaluations). The algorithm yields competitive results on both unimodal and multimodal benchmarks. Copyright 2009 ACM.
Original languageEnglish (US)
Title of host publicationProceedings of the 11th Annual Genetic and Evolutionary Computation Conference, GECCO-2009
Pages539-545
Number of pages7
DOIs
StatePublished - Dec 31 2009
Externally publishedYes

Bibliographical note

Generated from Scopus record by KAUST IRTS on 2022-09-14

Fingerprint

Dive into the research topics of 'Efficient natural evolution strategies'. Together they form a unique fingerprint.

Cite this