Learning emotions in virtual environments

Mannes Poel, Hendrikus J.A. op den Akker, Antinus Nijholt, A.J. van Kesteren, A.-J. van Kesteren

    Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

    44 Downloads (Pure)


    A modular hybrid neural network architecture, called SHAME, for emotion learning is introduced. The system learns from annotated data how the emotional state is generated and changes due to internal and external stimuli. Part of the modular architecture is domain independent and part must be adapted to the domain under consideration. The generation and learning of emotions is based on the event appraisal model. The architecture is implemented in a prototype consisting of agents trying to survive in a virtual world. An evaluation of this prototype shows that the architecture is capable of generating natural emotions and furthermore that training of the neural network modules in the architecture is computationally feasible. Keywords: hybrid neural systems, emotions, learning, agents.
    Original languageUndefined
    Title of host publicationCybernetics and Systems 2002
    EditorsR. Trappl
    Place of PublicationVienna
    PublisherAustrian Society for Cybernetic Studies
    Number of pages5
    ISBN (Print)3-85206-160-1
    Publication statusPublished - 2002
    Event16th European Meeting on Cybernetics and Systems Research 2002 - University of Vienna, Vienna, Austria
    Duration: 2 Apr 20025 Apr 2002
    Conference number: 16

    Publication series

    PublisherAustrian Society for Cybernetic Studies


    Conference16th European Meeting on Cybernetics and Systems Research 2002
    Abbreviated titleCybernetics and Systems


    • EWI-6672
    • METIS-209273
    • IR-66305
    • HMI-IA: Intelligent Agents
    • HMI-CI: Computational Intelligence

    Cite this