Evolving small neurocontrollers with self-organized compact encoding

Shlomy Boshy, Eytan Ruppin

Research output: Contribution to journalArticlepeer-review

Abstract

This article presents a novel method for the evolution of artificial autonomous agents with small neurocontrollers. It is based on adaptive, self-organized compact genotypic encoding (SOCE) generating the phenotype synaptic weights of the agent's neurocontroller SOCE implements a parallel evolutionary search for neurocontroller solutions in a dynamically varying and reduced subspace of the original synaptic space. It leads to the emergence of compact successful neurocontrollers starting from large networks. The method can serve to estimate the network size needed to perform a given task, and to delineate the relative importance of the neutrons composing the agent's controller network.

Original languageEnglish
Pages (from-to)131-151
Number of pages21
JournalArtificial Life
Volume9
Issue number2
DOIs
StatePublished - 2003

Fingerprint

Dive into the research topics of 'Evolving small neurocontrollers with self-organized compact encoding'. Together they form a unique fingerprint.

Cite this