A Characterization of Sapient Agents

M. van Otterlo, Marco Wiering, Mehdi Dastani, John-Jules Meyer

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

    172 Downloads (Pure)


    This paper presents a proposal to characterize Sapient Agents in terms of cognitive concepts and abilities. In particular, a sapient agent is considered as a cognitive agent the learns its cognitive state and capabilities through experience. This characterization is based on formal concepts such as beliefs, goals, plans and reasoning rules, and formal techniques such as relational RL. We identify several aspects of cognitive agents that can be evolved through learning and indicate how these aspects can be learned. Other important features such as the social environment, interaction with other agents or humans and the ability to deal with emotions, will also be discussed. The paper ends with directions for further research on sapient agents.
    Original languageUndefined
    Title of host publicationInternational Conference Integration of Knowledge Intensive Multi-Agent Systems (KIMAS-03)
    EditorsH. Hexmoor
    Place of PublicationBoston
    PublisherIEEE Computer Society
    Number of pages6
    ISBN (Print)0-7803-7958-6
    Publication statusPublished - 1 Oct 2003
    EventKIMAS'03, Boston, Massachusetts, USA: Proceedings of the International Conference of Knowledge Intensive Multi-Agent Systems (KIMAS'03) -
    Duration: 1 Jan 1900 → …

    Publication series



    ConferenceKIMAS'03, Boston, Massachusetts, USA
    Period1/01/00 → …


    • sapient agent characterization
    • EWI-14877
    • agent interaction
    • HMI-CI: Computational Intelligence
    • Decision Making
    • Multi-Agent Systems
    • social environment
    • cognitive agent
    • IR-46483
    • learning (artificial intelligence)
    • METIS-215158
    • reasoning rules
    • Cognition
    • relational reinforcement learning

    Cite this