Challenges for Relational Reinforcement Learning

M. van Otterlo, Kristian Kersting

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

    83 Downloads (Pure)

    Abstract

    We present a perspective and challenges for Relational Reinforcement Learning (RRL). We first survey existing work and distinguish a number of main directions. We then highlight some research problems that are intrinsically involved in abstracting over relational Markov Decision Processes. These are the challenges of RRL. In addition, we describe a number of issues that will be important for further research into RRL. These are the challenges for RRL and deal with newly arising issues because of relational abstraction.
    Original languageEnglish
    Title of host publicationProceedings of the Workshop on Relational Reinforcement Learning at ICML'04
    EditorsP. Tadepalli, R Givan, K. Driessens
    Place of PublicationCorvallis
    PublisherUniversity of Alberta
    Pages74-80
    Number of pages7
    Publication statusPublished - 8 Jul 2004
    EventWorkshop on Relational Reinforcement Learning 2004 - Banff, Canada
    Duration: 4 Jul 20048 Jul 2004

    Workshop

    WorkshopWorkshop on Relational Reinforcement Learning 2004
    CountryCanada
    CityBanff
    Period4/07/048/07/04

    Keywords

    • EWI-13095
    • IR-64887
    • METIS-221213
    • HMI-IA: Intelligent Agents

    Fingerprint Dive into the research topics of 'Challenges for Relational Reinforcement Learning'. Together they form a unique fingerprint.

  • Cite this

    van Otterlo, M., & Kersting, K. (2004). Challenges for Relational Reinforcement Learning. In P. Tadepalli, R. Givan, & K. Driessens (Eds.), Proceedings of the Workshop on Relational Reinforcement Learning at ICML'04 (pp. 74-80). Corvallis: University of Alberta.