TY  - JOUR
A1  - Weber, Cornelius
T1  - 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
T2  - Frontiers in neurorobotics
N2  - 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. ...
Y1  - 2008
UR  - http://publikationen.ub.uni-frankfurt.de/frontdoor/index/index/docId/6028
UR  - https://nbn-resolving.org/urn:nbn:de:hebis:30-58710
SN  - 1662-5218
N1  - 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.
N1  - 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
VL  - 2
IS  - Art. 1
SP  - 1
EP  - 1
PB  - Frontiers Research Foundation
CY  - Lausanne
ER  -