ML Anthology

Efficient Skill Learning Using Abstraction Selection

George Dimitri Konidaris, Andrew G. Barto
IJCAI 2009 pp. 1107-1112
/ijcai/2009/konidaris2009ijcai-efficient/

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. George Konidaris, Andrew Barto

PDF Semantic Scholar

Cite

Text

Konidaris and Barto. "Efficient Skill Learning Using Abstraction Selection." International Joint Conference on Artificial Intelligence, 2009.

Markdown

[Konidaris and Barto. "Efficient Skill Learning Using Abstraction Selection." International Joint Conference on Artificial Intelligence, 2009.](https://mlanthology.org/ijcai/2009/konidaris2009ijcai-efficient/)

BibTeX

@inproceedings{konidaris2009ijcai-efficient,
  title     = {{Efficient Skill Learning Using Abstraction Selection}},
  author    = {Konidaris, George Dimitri and Barto, Andrew G.},
  booktitle = {International Joint Conference on Artificial Intelligence},
  year      = {2009},
  pages     = {1107-1112},
  url       = {https://mlanthology.org/ijcai/2009/konidaris2009ijcai-efficient/}
}