An Information-Theoretic Approach for the Quantification of Relevance

Authors:
Daniel Polani;Thomas Martinetz;Jan T. Kim
Affiliations:
-;-;-
Venue:
ECAL '01 Proceedings of the 6th European Conference on Advances in Artificial Life
Year:
2001

Citing 6
Cited 0

A framework for sensor evolution in a population of Braitenberg vehicle-like agents (poster)

ALIFE Proceedings of the sixth international conference on Artificial life
Dynamic Programming and Stochastic Control

Dynamic Programming and Stochastic Control
Introduction to Reinforcement Learning

Introduction to Reinforcement Learning
Some Effects of Individual Learning on the Evolution of Sensors

ECAL '01 Proceedings of the 6th European Conference on Advances in Artificial Life
Reinforcement learning: a survey

Journal of Artificial Intelligence Research
A graph-theoretic analysis of information value

UAI'96 Proceedings of the Twelfth international conference on Uncertainty in artificial intelligence

Quantified Score

Hi-index	0.00

Visualization

Abstract

We propose a concept for a Shannon-type quantification of information relevant to a decision unit or agent. The proposed measure is operational, can - at least in principle - be calculated for a given system and has an immediate interpretation as an information quantity. Its use as a natural framework for the study of sensor evolution is discussed.