Bellman goes Relational (extended abstract)

M. van Otterlo, Kristian Kersting, Luc De Raedt

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

    19 Downloads (Pure)

    Abstract

    We introduce REBEL, a relational Bellman update operator that can be used for Markov Decision Processes in - possibly infinite - relational domains. Using REBEL we develop a relational value iteration algorithm.
    Original languageUndefined
    Title of host publicationProceedings of the 16th Belgium-Netherlands Artificial Intelligence Conference (BNAIC'04)
    EditorsR. Verbrugge, N. Taatgen, L. Schonmaker
    Place of PublicationGroningen
    PublisherUniversity of Groningen
    Pages287-288
    Number of pages2
    Publication statusPublished - 21 Oct 2004
    Event16th Belgium-Dutch Conference on Artificial Intelligence, BNAIC 2004 - Groningen, Netherlands
    Duration: 21 Oct 200422 Oct 2004
    Conference number: 16

    Publication series

    Name
    PublisherUniversity of Groningen

    Conference

    Conference16th Belgium-Dutch Conference on Artificial Intelligence, BNAIC 2004
    Abbreviated titleBNAIC
    CountryNetherlands
    CityGroningen
    Period21/10/0422/10/04

    Keywords

    • EWI-12988
    • IR-64848
    • METIS-221214
    • HMI-IA: Intelligent Agents

    Cite this