University of Sussex
Browse

File(s) not publicly available

The Dynamics of Associative Learning in an Evolved Situated Agent

presentation
posted on 2023-06-08, 09:28 authored by Eduardo Izquierdo, Inman HarveyInman Harvey
Artificial agents controlled by dynamic recurrent node net- works with fixed weights are evolved to search for food and associate it with one of two different temperatures depending on experience. The task requires either instrumental or classical conditioned responses to be learned. The paper extends previous work in this area by requiring that a situated agent be capable of re-learning during its lifetime. We anal- yse the best-evolved agents behaviour and explain in some depth how it arises from the dynamics of the coupled agent-environment system.

History

Publication status

  • Published

Publisher

Springer-Verlag

Pages

365.0

Presentation Type

  • paper

Event name

Proceedings of European Conference on Artificial Life, 2007

Event location

Lisbon

Event type

conference

ISBN

978-3-540-74912-7

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