Header logo is ei

Abstraction in Decision-Makers with Limited Information Processing Capabilities


Conference Paper


A distinctive property of human and animal intelligence is the ability to form abstractions by neglecting irrelevant information which allows to separate structure from noise. From an information theoretic point of view abstractions are desirable because they allow for very efficient information processing. In artificial systems abstractions are often implemented through computationally costly formations of groups or clusters. In this work we establish the relation between the free-energy framework for decision-making and rate-distortion theory and demonstrate how the application of rate-distortion for decision-making leads to the emergence of abstractions. We argue that abstractions are induced due to a limit in information processing capacity.

Author(s): Genewein, T and Braun, DA
Pages: 1-9
Year: 2013
Month: December

Department(s): Empirical Inference
Bibtex Type: Conference Paper (conference)

Event Name: NIPS 2013 Workshop Planning with Information Constraints for Control, Reinforcement Learning, Computational Neuroscience, Robotics and Games
Event Place: Lake Tahoe, NV, USA

URL: http://www.kyb.tuebingen.mpg.defileadmin/user_upload/files/publications/2013/NIPS-2013-Workshop-Genewein.pdf


  title = {Abstraction in Decision-Makers with Limited Information Processing Capabilities},
  author = {Genewein, T and Braun, DA},
  pages = {1-9},
  month = dec,
  year = {2013},
  url = {http://www.kyb.tuebingen.mpg.defileadmin/user_upload/files/publications/2013/NIPS-2013-Workshop-Genewein.pdf},
  month_numeric = {12}