KIT | KIT-Bibliothek | Impressum
Open Access Logo
§
Volltext
URN: urn:nbn:de:swb:90-AAA306520018

Hierarchical reinforcement learning with multi-step actions

Schoknecht, Ralf

Abstract:

In recent years hierarchical concepts of temporal abstraction
have been integrated in the reinforcement learning framework to
improve scalability. However, existing approaches are limited to
domains for which a decomposition in subtasks is known a priori.
In this paper we propose the concept of multi-step actions on
different time scales in one single action set. It is suited for
learning optimal policies in unstructured domains where a
decomposition is not known in advance or does not exist at all.
At the same time this approach enables learning at multiple
levels of temporal abstraction. Thus, multi-step actions offer
the possibility to obtain faster learning algorithms for
unstructured domains.


Zugehörige Institution(en) am KIT Institut für Logik, Komplexität und Deduktionssysteme (ILKD)
Publikationstyp Buchaufsatz
Jahr 2001
Sprache Englisch
Identifikator URN: urn:nbn:de:swb:90-AAA306520018
KITopen ID: 30652001
Erscheinungsvermerk In: Proceedings. Workshop on Hierarchy and Memory in Reinforcement Learning, 18th International Conference on Machine Learning, Williams College, Williamstown, Mass. 2001 [online].
KIT – Die Forschungsuniversität in der Helmholtz-Gemeinschaft KITopen Landing Page