Motivation Driven Learning of Action Affordances

I. Cos-Aguilera, Lola Cañamero, G. Hayes

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

    1 Citation (Scopus)
    182 Downloads (Pure)

    Abstract

    Survival in the animal realm often depends on the ability to elucidate the potentialities for action offered by every situation. This paper argues that affordance learning is a powerful ability for adaptive, embodied, situated agents, and presents a motivation-driven method for their learning. The method proposed considers the agent and its environment as a single unit, thus intrinsically relating agent's interactions to fluctuations of the agent's internal motivation. Being that the motivational state is an expression of the agent's physiology, the existing causality of interactions and their effect on the motivational state is exploited as a principle to learn object affordances. The hypothesis is tested in a Webots 4.0 simulator with a Khepera robot.
    Original languageEnglish
    Title of host publicationProcs of Symposium on Agents that Want and Like - Motivational and Emotional Roots of Cognition and Action
    Subtitle of host publicationAISB'05
    PublisherThe Society for the Study of Artificial Intelligence and the Simulation of Behaviour (AISB)
    Pages33-36
    ISBN (Print)1-902956-41-7
    Publication statusPublished - 2005
    EventSSAISB Convention 2005 - Hatfield, United Kingdom
    Duration: 12 Apr 200515 Apr 2005

    Conference

    ConferenceSSAISB Convention 2005
    Country/TerritoryUnited Kingdom
    CityHatfield
    Period12/04/0515/04/05

    Fingerprint

    Dive into the research topics of 'Motivation Driven Learning of Action Affordances'. Together they form a unique fingerprint.

    Cite this