Frontiers in Robotics and AI (Nov 2015)

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

  • Tim eGenewein,
  • Tim eGenewein,
  • Tim eGenewein,
  • Felix eLeibfried,
  • Felix eLeibfried,
  • Felix eLeibfried,
  • Jordi eGrau-Moya,
  • Jordi eGrau-Moya,
  • Jordi eGrau-Moya,
  • Daniel Alexander Braun,
  • Daniel Alexander Braun

DOI
https://doi.org/10.3389/frobt.2015.00027
Journal volume & issue
Vol. 2

Abstract

Read online

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.

Keywords