Constructing Abstraction Hierarchies Using a Skill-Symbol Loop
Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence. Pages 1648-1653.
Abstract
We describe a framework for building abstraction hierarchies whereby an agent alternates skill- and representation-construction phases to construct a sequence of increasingly abstract Markov decision processes. Our formulation builds on recent results showing that the appropriate abstract representation of a problem is specified by the agent's skills. We describe how such a hierarchy can be used for fast planning, and illustrate the construction of an appropriate hierarchy for the Taxi domain.
George Dimitri Konidaris. 2016. Constructing Abstraction Hierarchies Using a Skill-Symbol Loop. In Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence, IJCAI-16. IJCAI, 1648–1653. https://ijcai.org/proceedings/2016/236
Konidaris, G. D. (2016). Constructing Abstraction Hierarchies Using a Skill-Symbol Loop. In Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence, IJCAI-16 (pp. 1648–1653). IJCAI. https://ijcai.org/proceedings/2016/236
@inproceedings{ijcai2016p236,
title = {Constructing Abstraction Hierarchies Using a Skill-Symbol Loop},
author = {Konidaris, George Dimitri},
booktitle = {Proceedings of the Twenty-Fifth International Joint Conference on
Artificial Intelligence, {IJCAI-16}},
publisher = {AAAI Press / International Joint Conferences on Artificial Intelligence},
editor = {Subbarao Kambhampati},
pages = {1648--1653},
year = {2016},
month = {7},
url = {https://ijcai.org/proceedings/2016/236},
}
TY - CPAPER TI - Constructing Abstraction Hierarchies Using a Skill-Symbol Loop AU - Konidaris, George Dimitri T2 - Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence, IJCAI-16 PB - AAAI Press / International Joint Conferences on Artificial Intelligence PY - 2016 SP - 1648 EP - 1653 UR - https://ijcai.org/proceedings/2016/236 ER -Copied
Machine-readable versions of this paper, for tools and AI agents: