Constructing abstraction hierarchies using a skill-symbol loop


Conference Paper

We describe a framework for building abstraction hierarchies whereby an agent alternates skill- and representation-construction phases to construct a sequence of increasingly abstract Markov decision processes. Our formulation builds on recent results showing that the appropriate abstract representation of a problem is specified by the agent's skills. We describe how such a hierarchy can be used for fast planning, and illustrate the construction of an appropriate hierarchy for the Taxi domain.

Duke Authors

Cited Authors

  • Konidaris, G

Published Date

  • January 1, 2016

Published In

Volume / Issue

  • 2016-January /

Start / End Page

  • 1648 - 1654

International Standard Serial Number (ISSN)

  • 1045-0823

Citation Source

  • Scopus