---
title: "Efficient Skill Learning Using Abstraction Selection"
authors:
  - "George Konidaris"
  - "Andrew Barto"
doi: ""
url: "https://ijcai.org/proceedings/2009/187"
pdf: "https://ijcai.org/proceedings/2009/0187.pdf"
venue: "Proceedings of the Twenty-First International Joint Conference on Artificial Intelligence"
year: 2009
pages: ""
track: ""
keywords:
---

# Efficient Skill Learning Using Abstraction Selection

George Konidaris, Andrew Barto

*Proceedings of the Twenty-First International Joint Conference on Artificial Intelligence*.

## Abstract

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.