Hierarchical strategy learning with hybrid representations

Sungwook Yoon, Subbarao Kambhampati

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

5 Scopus citations

Abstract

Good problem solving knowledge for real life domains is hard to define in a single representation. In some situations, a direct policy is a better choice while in others, value function is better. Typically, direct policy representation is better suited to strategic level plans, while value function representation is better suited to tactical level plans. We propose a hybrid hierarchical representation machine (HHRM) where direct policy representation and value function based representation can co-exist in a level-wise fashion. We provide simple learning and planning algorithms with our new representation and discuss their application to Airspace Deconfliction domain. In our experiments, we provided our system LSP with two level HHRM for the domain. LSP could successfully learn from limited number of experts' solution traces and show superior performance compared to average of human novice learners.

Original languageEnglish (US)
Title of host publicationAcquiring Planning Knowledge via Demonstration - Papers from the 2007 AAAI Workshop, Technical Report
Pages52-56
Number of pages5
StatePublished - Dec 1 2007
Event2007 AAAI Workshop - Vancouver, BC, Canada
Duration: Jul 23 2007Jul 23 2007

Publication series

NameAAAI Workshop - Technical Report
VolumeWS-07-02

Other

Other2007 AAAI Workshop
CountryCanada
CityVancouver, BC
Period7/23/077/23/07

    Fingerprint

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Yoon, S., & Kambhampati, S. (2007). Hierarchical strategy learning with hybrid representations. In Acquiring Planning Knowledge via Demonstration - Papers from the 2007 AAAI Workshop, Technical Report (pp. 52-56). (AAAI Workshop - Technical Report; Vol. WS-07-02).