An Evolving Ecosystems Approach to Generating Complex Agent Behaviour

P.P. Pichler, L. Canamero

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

    3 Citations (Scopus)
    36 Downloads (Pure)

    Abstract

    We propose an evolving ecosystem approach to
    evolving complex agent behaviour based on the principle of natural
    selection. The agents start with very limited functional design
    and morphology and neural controllers are concurrently evolved
    as functional wholes. The agents are ‘grounded’ in an increasingly
    complex environment by a complex model metabolism and interaction
    dynamics. Furthermore, we introduce a novel criterion for
    evaluating differential reproductive success aimed at maximising
    evolutionary freedom. We also present first experimental results
    suggesting that this approach may be conducive to widening the
    scope of artificial evolution for the generation of agents exhibiting
    non-trivial behaviours in a complex ecosystem.
    Original languageEnglish
    Title of host publicationProcs of the 2007 IEEE Symposium on Artificial Life (CI-SLife 2007)
    PublisherInstitute of Electrical and Electronics Engineers (IEEE)
    Pages303-310
    Publication statusPublished - 2007

    Fingerprint

    Dive into the research topics of 'An Evolving Ecosystems Approach to Generating Complex Agent Behaviour'. Together they form a unique fingerprint.

    Cite this