Abstract

In this work, we analyse the performance of Novelty Search (NS) in a set of generalization experiments in a navigation task with Grammatical Evolution. Agents are trained on a single, simple environment, and tested on a selection of related, increasingly more difficult environments. We show that agents discovered with NS, although using a tiny number (six) of training samples, successfully generalise to these more difficult environments.

Original languageEnglish
Title of host publicationGECCO 2020 Companion - Proceedings of the 2020 Genetic and Evolutionary Computation Conference Companion
PublisherAssociation for Computing Machinery, Inc
Pages243-244
Number of pages2
ISBN (Electronic)9781450371278
DOIs
Publication statusPublished - 8 Jul 2020
Event2020 Genetic and Evolutionary Computation Conference, GECCO 2020 - Cancun, Mexico
Duration: 8 Jul 202012 Jul 2020

Publication series

NameGECCO 2020 Companion - Proceedings of the 2020 Genetic and Evolutionary Computation Conference Companion

Conference

Conference2020 Genetic and Evolutionary Computation Conference, GECCO 2020
Country/TerritoryMexico
CityCancun
Period8/07/2012/07/20

Keywords

  • Generalization
  • Grammatical evolution
  • Novelty search

Fingerprint

Dive into the research topics of 'General controllers evolved through grammatical evolution with a divergent search'. Together they form a unique fingerprint.

Cite this