D-CIS Publication Database

Publication

Type of publication:Inproceedings
Entered by:MvI
Title
Bibtex cite ID
Booktitle NIPS workshop Hierarchical methods
Year published 2007
Month December
Location Vancouver, Canada
Keywords reinforcement learning,multiple qualitatively different state representations
Abstract
This paper proposes a reinforcement learning architecture containing multiple "experts", each of which is a specialist in a different region in the overall state space. The central idea is that the different experts use qualitatively different (but sufficiently Markov) state representations, each of which captures different information regarding the true underlying world state, and which for that reason is suitable for a different part of the state space. The experts themselves learn to switch to another state representation (other expert) by having switching actions. Value functions can be learned using standard reinforcement learning algorithms. Experiments in a small, proof-of-principle experiment as well as a larger, more realistic experiment illustrate the validity of this approach.
Authors
van Seijen, Harm
Bakker, Bram
Kester, Leon
Topics
=SEE CLASSIFICATION DIFFERENCE FROM OTHERS=
BibTeXBibTeX
RISRIS
Attachments
Seijen_etal_nips_hierarchyworkshop.pdf (main file)
 
Total mark: 5