Relational Representations in Reinforcement Learning: Review and Open Problems

M. van Otterlo

    Research output: Contribution to conferencePaperpeer-review

    126 Downloads (Pure)

    Abstract

    This paper is about representation in RL.We discuss some of the concepts in representation and generalization in reinforcement learning and argue for higher-order representations, instead of the commonly used propositional representations. The paper contains a small review of current reinforcement learning systems using higher-order representations, followed by a brief discussion. The paper ends with research directions and open problems.
    Original languageEnglish
    Number of pages8
    Publication statusPublished - 9 Jul 2002
    EventICML-2002 Workshop on Development of Representations - University of New South Wales, Sydney, Australia
    Duration: 9 Jul 20029 Jul 2002
    http://www.demo.cs.brandeis.edu/icml02ws/

    Workshop

    WorkshopICML-2002 Workshop on Development of Representations
    CountryAustralia
    CitySydney
    Period9/07/029/07/02
    Internet address

    Keywords

    • EWI-14945
    • Review
    • relational representations
    • HMI-IA: Intelligent Agents
    • IR-65334
    • Generalization
    • Reinforcement learning

    Fingerprint

    Dive into the research topics of 'Relational Representations in Reinforcement Learning: Review and Open Problems'. Together they form a unique fingerprint.

    Cite this