English

Abstraction in decision-makers with limited information processing capabilities

Artificial Intelligence 2013-12-20 v2 Information Theory math.IT Machine Learning

Abstract

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.

Keywords

Cite

@article{arxiv.1312.4353,
  title  = {Abstraction in decision-makers with limited information processing capabilities},
  author = {Tim Genewein and Daniel A. Braun},
  journal= {arXiv preprint arXiv:1312.4353},
  year   = {2013}
}

Comments

Presented at the NIPS 2013 Workshop on Planning with Information Constraints

R2 v1 2026-06-22T02:28:23.785Z