Symbol acquisition for probabilistic high-level planning

Published

Conference Paper

We introduce a framework that enables an agent to autonomously learn its own symbolic representation of a low-level, continuous environment. Propositional symbols are formalized as names for probability distributions, providing a natural means of dealing with uncertain representations and probabilistic plans. We determine the symbols that are sufficient for computing the probability with which a plan will succeed, and demonstrate the acquisition of a symbolic representation in a computer game domain.

Duke Authors

Cited Authors

  • Konidaris, G; Kaelbling, LP; Lozano-Perez, T

Published Date

  • January 1, 2015

Published In

Volume / Issue

  • 2015-January /

Start / End Page

  • 3619 - 3627

International Standard Serial Number (ISSN)

  • 1045-0823

International Standard Book Number 13 (ISBN-13)

  • 9781577357384

Citation Source

  • Scopus