English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
  Bounded rationality, abstraction and hierarchical decision-making: an information-theoretic optimality principle

Genewein, T., Leibfried, F., Grau-Moya, J., & Braun, D. (2015). Bounded rationality, abstraction and hierarchical decision-making: an information-theoretic optimality principle. Frontiers in Robotics and AI, 2: 27, pp. 1-24. doi:10.3389/frobt.2015.00027.

Item is

Files

show Files

Locators

show

Creators

show
hide
 Creators:
Genewein, T1, 2, Author              
Leibfried, F1, 2, Author              
Grau-Moya, J1, 2, Author              
Braun, DA1, 2, Author              
Affiliations:
1Research Group Sensorimotor Learning and Decision-Making, Max Planck Institute for Biological Cybernetics, Max Planck Society, ou_1497809              
2Max Planck Institute for Biological Cybernetics, Max Planck Society, Spemannstrasse 38, 72076 Tübingen, DE, ou_1497794              

Content

show
hide
Free keywords: -
 Abstract: Abstraction and hierarchical information-processing are hallmarks of human and animal intelligence underlying the unrivaled flexibility of behavior in biological systems. Achieving such a flexibility in artificial systems is challenging, even with more and more computational power. Here we investigate the hypothesis that abstraction and hierarchical information-processing might in fact be the consequence of limitations in information-processing power. In particular, we study an information-theoretic framework of bounded rational decision-making that trades off utility maximization against information-processing costs. We apply the basic principle of this framework to perception-action systems with multiple information-processing nodes and derive bounded optimal solutions. We show how the formation of abstractions and decision-making hierarchies depends on information-processing costs. We illustrate the theoretical ideas with example simulations and conclude by formalizing a mathematically unifying optimization principle that could potentially be extended to more complex systems.

Details

show
hide
Language(s):
 Dates: 2015-10
 Publication Status: Published online
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Type: -
 Identifiers: DOI: 10.3389/frobt.2015.00027
BibTex Citekey: GeneweinLGB2015
 Degree: -

Event

show

Legal Case

show

Project information

show

Source 1

show
hide
Title: Frontiers in Robotics and AI
Source Genre: Journal
 Creator(s):
Affiliations:
Publ. Info: Lausanne : Frontiers Media
Pages: - Volume / Issue: 2 Sequence Number: 27 Start / End Page: 1 - 24 Identifier: ISSN: 2296-9144
CoNE: https://pure.mpg.de/cone/journals/resource/22969144