Autonomous parsing of behavior in a multi-agent setting

D. Vanderelst, E.I. Barakova

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

    1 Citation (Scopus)

    Abstract

    Imitation learning is a promising route to instruct robotic multi-agent systems. However, imitating agents should be able to decide autonomously what behavior, observed in others, is interesting to copy. Here we investigate whether a simple recurrent network (Elman net) can be used to extract meaningful chunks from a continuous sequence of observed actions. Results suggest that, even in spite of the high level of task specific noise, Elman nets can be used for isolating re-occurring action patterns in robots. Limitations and future directions are discussed.
    Original languageEnglish
    Title of host publicationIntelligent Systems 2008 : IS '08 ; 4th International IEEE Conference, 6-8 September, 2008, Varna, Bulgaria
    Place of PublicationPiscataway
    PublisherInstitute of Electrical and Electronics Engineers
    Pages10-7-10-13
    Volume2
    ISBN (Print)978-1-4244-1739-1
    DOIs
    Publication statusPublished - 2008
    Eventconference; IS '08 : Intelligent Systems 2008 ; 4th International IEEE Conference, 6-8 September, 2008, Varna, Bulgaria -
    Duration: 1 Jan 2008 → …

    Conference

    Conferenceconference; IS '08 : Intelligent Systems 2008 ; 4th International IEEE Conference, 6-8 September, 2008, Varna, Bulgaria
    Period1/01/08 → …
    OtherIS '08 : Intelligent Systems 2008 ; 4th International IEEE Conference, 6-8 September, 2008, Varna, Bulgaria

    Fingerprint Dive into the research topics of 'Autonomous parsing of behavior in a multi-agent setting'. Together they form a unique fingerprint.

    Cite this