Teaching and executing verb phrases

Daniel Hewlett, Thomas J. Walsh, Paul Cohen

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    4 Scopus citations

    Abstract

    This paper describes a framework for an agent to learn models of verb-phrase meanings from human teachers and combine these models with environmental dynamics to enact verb commands. The framework extends prior work in apprenticeship learning and leverages recent advancements in modeling activities and planning in domains with multiple objects. We show how to both learn a verb model as a relational finite state machine and how to turn this model into reward and heuristic functions that can then be composed with an MDP model of an environment. The resulting "combined model" can then be efficiently searched by a planner to enact a verb command in this environment. Our experiments in simulated robot domains show this framework can be used to quickly teach verb commands and improves over the current state of the art method.

    Original languageEnglish (US)
    Title of host publication2011 IEEE International Conference on Development and Learning, ICDL 2011
    DOIs
    StatePublished - 2011
    Event2011 IEEE International Conference on Development and Learning, ICDL 2011 - Frankfurt am Main, Germany
    Duration: Aug 24 2011Aug 27 2011

    Publication series

    Name2011 IEEE International Conference on Development and Learning, ICDL 2011

    Other

    Other2011 IEEE International Conference on Development and Learning, ICDL 2011
    Country/TerritoryGermany
    CityFrankfurt am Main
    Period8/24/118/27/11

    ASJC Scopus subject areas

    • Electrical and Electronic Engineering
    • Education

    Fingerprint

    Dive into the research topics of 'Teaching and executing verb phrases'. Together they form a unique fingerprint.

    Cite this