Hierarchical behaviours : getting the most bang for your bit

S. van Dijk, D. Polani, C.L. Nehaniv

    Research output: Contribution to journalArticlepeer-review

    10 Citations (Scopus)
    43 Downloads (Pure)


    Hierarchical structuring of behaviour is prevalent in natural and artificial agents and can be shown to be useful for learning and performing tasks. To progress systematic understanding of these benefits we study the effect of hierarchical architectures on the required information processing capability of an optimally acting agent. We show that an information-theoretical approach provides important insights into why factored and layered behaviour structures are beneficial.
    Original languageEnglish
    Pages (from-to)342-349
    JournalLecture Notes in Computer Science (LNCS)
    Publication statusPublished - 2011
    EventEuropean Conference on Artificial Life - Budapest, United Kingdom
    Duration: 13 Sept 200916 Sept 2009


    Dive into the research topics of 'Hierarchical behaviours : getting the most bang for your bit'. Together they form a unique fingerprint.

    Cite this