How do we approach intrinsic motivation computationally? : a commentary on: What is intrinsic motivation? A typology of computational approaches. by Pierre-Yves Oudeyer and Frederic Kaplan

  • What is the energy function guiding behavior and learningµ Representationbased approaches like maximum entropy, generative models, sparse coding, or slowness principles can account for unsupervised learning of biologically observed structure in sensory systems from raw sensory data. However, they do not relate to behavior. Behavior-based approaches like reinforcement learning explain animal behavior in well-described situations. However, they rely on high-level representations which they cannot extract from raw sensory data. Combinations of multiple goal functions seems the methodology of choice to understand the complexity of the brain. But what is the set of possible goals. ...

Download full text files

Export metadata

Metadaten
Author:Cornelius Weber
URN:urn:nbn:de:hebis:30-58710
DOI:https://doi.org/doi:10.3389/neuro.12.001.2008
ISSN:1662-5218
Pubmed Id:https://pubmed.ncbi.nlm.nih.gov/20827402
Parent Title (English):Frontiers in neurorobotics
Publisher:Frontiers Research Foundation
Place of publication:Lausanne
Contributor(s):Pierre-Yves Oudeyer, Frederic Kaplan
Document Type:Article
Language:English
Year of Completion:2008
Date of first Publication:2008/05/22
Publishing Institution:Universitätsbibliothek Johann Christian Senckenberg
Release Date:2008/11/14
Volume:2
Issue:Art. 1
Page Number:1
First Page:1
Last Page:1
Note:
Copyright: © 2008 Weber. This is an open-access commentary subject to an exclusive license agreement between the authors and the Frontiers Research Foundation, which permits unrestricted use, distribution, and reproduction in any medium, provided the original authors and source are credited.
Note:
Kommentar zu: What is intrinsic motivation? : a typology of computational approaches / Pierre-Yves Oudeyer ; Frederic Kaplan, in: Frontiers in neurorobotics, 1.2007, Art. 6, doi:10.3389/neuro.12.006.2007
HeBIS-PPN:206779844
Institutes:Wissenschaftliche Zentren und koordinierte Programme / Frankfurt Institute for Advanced Studies (FIAS)
Dewey Decimal Classification:0 Informatik, Informationswissenschaft, allgemeine Werke / 00 Informatik, Wissen, Systeme / 004 Datenverarbeitung; Informatik
Licence (German):License LogoDeutsches Urheberrecht

OPUS4 Logo