Constructing abstraction hierarchies using a skill-symbol loop
Publication
, Conference
Konidaris, G
Published in: IJCAI International Joint Conference on Artificial Intelligence
January 1, 2016
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.
Duke Scholars
Published In
IJCAI International Joint Conference on Artificial Intelligence
ISSN
1045-0823
Publication Date
January 1, 2016
Volume
2016-January
Start / End Page
1648 / 1654
Citation
APA
Chicago
ICMJE
MLA
NLM
Konidaris, G. (2016). Constructing abstraction hierarchies using a skill-symbol loop. In IJCAI International Joint Conference on Artificial Intelligence (Vol. 2016-January, pp. 1648–1654).
Konidaris, G. “Constructing abstraction hierarchies using a skill-symbol loop.” In IJCAI International Joint Conference on Artificial Intelligence, 2016-January:1648–54, 2016.
Konidaris G. Constructing abstraction hierarchies using a skill-symbol loop. In: IJCAI International Joint Conference on Artificial Intelligence. 2016. p. 1648–54.
Konidaris, G. “Constructing abstraction hierarchies using a skill-symbol loop.” IJCAI International Joint Conference on Artificial Intelligence, vol. 2016-January, 2016, pp. 1648–54.
Konidaris G. Constructing abstraction hierarchies using a skill-symbol loop. IJCAI International Joint Conference on Artificial Intelligence. 2016. p. 1648–1654.
Published In
IJCAI International Joint Conference on Artificial Intelligence
ISSN
1045-0823
Publication Date
January 1, 2016
Volume
2016-January
Start / End Page
1648 / 1654