Efficient skill learning using abstraction selection
Publication
, Journal Article
Konidaris, G; Barto, A
Published in: Ijcai International Joint Conference on Artificial Intelligence
January 1, 2009
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 Scholars
Published In
Ijcai International Joint Conference on Artificial Intelligence
ISSN
1045-0823
Publication Date
January 1, 2009
Start / End Page
1107 / 1112
Citation
APA
Chicago
ICMJE
MLA
NLM
Konidaris, G., & Barto, A. (2009). Efficient skill learning using abstraction selection. Ijcai International Joint Conference on Artificial Intelligence, 1107–1112.
Konidaris, G., and A. Barto. “Efficient skill learning using abstraction selection.” Ijcai International Joint Conference on Artificial Intelligence, January 1, 2009, 1107–12.
Konidaris G, Barto A. Efficient skill learning using abstraction selection. Ijcai International Joint Conference on Artificial Intelligence. 2009 Jan 1;1107–12.
Konidaris, G., and A. Barto. “Efficient skill learning using abstraction selection.” Ijcai International Joint Conference on Artificial Intelligence, Jan. 2009, pp. 1107–12.
Konidaris G, Barto A. Efficient skill learning using abstraction selection. Ijcai International Joint Conference on Artificial Intelligence. 2009 Jan 1;1107–1112.
Published In
Ijcai International Joint Conference on Artificial Intelligence
ISSN
1045-0823
Publication Date
January 1, 2009
Start / End Page
1107 / 1112