LiU Electronic Press
Full-text not available in DiVA
Author:
Nyblom, Per (Linköping University, Department of Computer and Information Science, KPLAB - Knowledge Processing Lab) (Linköping University, The Institute of Technology)
Title:
Dynamic Abstraction for Hierarchical Problem Solving and Execution in Stochastic Dynamic Environments
Department:
Linköping University, Department of Computer and Information Science, KPLAB - Knowledge Processing Lab
Linköping University, The Institute of Technology
Publication type:
Conference paper (Refereed)
Language:
English
In:
STAIRS 2006
Editor:
Loris Penserini, Pavlos Peppas, Anna Perini
Conference:
3rd Starting Artificial Intelligence Researchers Symposium (STAIRS 2006), 28-29 August 2006, Riva del Garda, Italy
Publisher: IOS Press
Series:
Frontiers in Artificial Intelligence and Applications, ISSN 0922-6389; 142
Volume:
142
Pages:
263-264
Year of publ.:
2006
URI:
urn:nbn:se:liu:diva-58465
Permanent link:
http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-58465
ISBN:
978-1-58603-645-4, e-978-1-60750-190-9
ISI:
000273476500029
Subject category:
Engineering and Technology
Abstract(en) :

Most of today’s autonomous problem solving agents perform their task with the help of problem domain specifications that keep their abstractions fixed. Those abstractions are often selected by human users. We think that the approach with fixed-abstraction domain specifications is very inflexible because it does not allow the agent to focus its limited computational resources on what may be most relevant at the moment. We would like to build agents that dynamically find suitable abstractions depending on relevance for their current task and situation. This idea of dynamic abstraction has recently been considered an important research problem within the area of hierarchical reinforcement learning [1].

Available from:
2010-08-12
Created:
2010-08-11
Last updated:
2013-06-26
Statistics:
30 hits