Advanced

Cognitive modeling with context sensitive reinforcement learning

Balkenius, Christian LU and Winberg, Stefan LU (2004) In Proceedings of AILS 04 ( Report / Lund Institute of Technology, Lund University ; 151) p.10-19
Abstract
We describe how a standard reinforcement learning algorithm can be changed to include a second contextual input that is used to modulate the learning in the original algorithm. The new algorithm takes the context into account during relearning when the previously learned actions are no longer valid. The algorithm was tested on a number of cognitive experiment and shown to reproduce the learning in both a task switching test and in the Wisconsin Card Sorting Test. In addition, the algorithm was able to learn a context sensitive categorization of objects in the Labov experiment.
Please use this url to cite or link to this publication:
author
organization
publishing date
type
Chapter in Book/Report/Conference proceeding
publication status
published
subject
in
Proceedings of AILS 04 ( Report / Lund Institute of Technology, Lund University ; 151)
editor
Malek, J. and
pages
10 - 19
publisher
Department of Computer Science, Lund University
ISSN
1650-1276
language
English
LU publication?
yes
id
cf0bf903-7770-4e51-993e-bc20240ac643 (old id 531323)
alternative location
http://www.lucs.lu.se/People/Christian.Balkenius/PDF/Balkenius.Winberg.2004.pdf
date added to LUP
2007-09-13 08:31:11
date last changed
2016-04-16 04:56:34
@inproceedings{cf0bf903-7770-4e51-993e-bc20240ac643,
  abstract     = {We describe how a standard reinforcement learning algorithm can be changed to include a second contextual input that is used to modulate the learning in the original algorithm. The new algorithm takes the context into account during relearning when the previously learned actions are no longer valid. The algorithm was tested on a number of cognitive experiment and shown to reproduce the learning in both a task switching test and in the Wisconsin Card Sorting Test. In addition, the algorithm was able to learn a context sensitive categorization of objects in the Labov experiment.},
  author       = {Balkenius, Christian and Winberg, Stefan},
  booktitle    = {Proceedings of AILS 04 ( Report / Lund Institute of Technology, Lund University ; 151)},
  editor       = {Malek, J.},
  issn         = {1650-1276},
  language     = {eng},
  pages        = {10--19},
  publisher    = {Department of Computer Science, Lund University},
  title        = {Cognitive modeling with context sensitive reinforcement learning},
  year         = {2004},
}