University of Sussex
Browse

File(s) not publicly available

Neutrality and ruggedness in robot landscapes

presentation
posted on 2023-06-08, 07:47 authored by T Smith, Andy PhilippidesAndy Philippides, Phil HusbandsPhil Husbands, M O'Shea
The twin fitness landscape properties of neutrality and ruggedness are crucial to the dynamics of evolutionary optimisation. In this paper, we investigate the interplay between these two properties in a complex evolutionary robotics fitness landscape, through the introduction of four robot controller architecture models; the GasNet, uniform, dispersed and plexus models. We show that, in isolation, neither added neutrality or decreased ruggedness (coupling) in the models produces increase in the speed of evolution. However, both effects in conjunction produce a significant increase in the speed of evolution

History

Publication status

  • Published

Publisher

IEEE Computer Society

Pages

8.0

Presentation Type

  • paper

Event name

Proceedings IEEE International Congress on Evolutionary Computing 2002

Event location

Honolulu, Hawaii

Event type

conference

ISBN

9780780372825

Department affiliated with

  • Informatics Publications

Full text available

  • No

Peer reviewed?

  • Yes

Legacy Posted Date

2012-02-06

Usage metrics

    University of Sussex (Publications)

    Categories

    No categories selected

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC