Efficient Skill Learning Using Abstraction Selection
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.
George Konidaris, and Andrew Barto. 2009. Efficient Skill Learning Using Abstraction Selection. In Proceedings of the Twenty-First International Joint Conference on Artificial Intelligence, IJCAI-09. IJCAI, https://ijcai.org/proceedings/2009/187
Konidaris, G., & Barto, A. (2009). Efficient Skill Learning Using Abstraction Selection. In Proceedings of the Twenty-First International Joint Conference on Artificial Intelligence, IJCAI-09. IJCAI. https://ijcai.org/proceedings/2009/187
@inproceedings{ijcai2009p187,
title = {Efficient Skill Learning Using Abstraction Selection},
author = {Konidaris, George and Barto, Andrew},
booktitle = {Proceedings of the Twenty-First International Joint Conference on
Artificial Intelligence, {IJCAI-09}},
publisher = {International Joint Conferences on Artificial Intelligence},
editor = {Hiroaki Kitano},
year = {2009},
url = {https://ijcai.org/proceedings/2009/187},
}
TY - CPAPER TI - Efficient Skill Learning Using Abstraction Selection AU - Konidaris, George AU - Barto, Andrew T2 - Proceedings of the Twenty-First International Joint Conference on Artificial Intelligence, IJCAI-09 PB - International Joint Conferences on Artificial Intelligence PY - 2009 UR - https://ijcai.org/proceedings/2009/187 ER -Copied
Machine-readable versions of this paper, for tools and AI agents:
