Efficient skill learning using abstraction selection


Journal Article

We present an algorithm for selecting an appropriate abstraction when learning a new skill. We show empirically that it can consistently select an appropriate abstraction using very little sample data, and that it significantly improves skill learning performance in a reasonably large real-valued reinforcement learning domain.

Duke Authors

Cited Authors

  • Konidaris, G; Barto, A

Published Date

  • December 1, 2009

Published In

Start / End Page

  • 1107 - 1112

International Standard Serial Number (ISSN)

  • 1045-0823

Citation Source

  • Scopus