| Autor: |
Genewein, T., Leibfried, F., Grau-Moya, J., Braun, D. |
| Jazyk: |
angličtina |
| Rok vydání: |
2015 |
| Předmět: |
|
| Zdroj: |
Frontiers in Robotics and AI |
| ISSN: |
2296-9144 |
| DOI: |
10.3389/frobt.2015.00027 |
| Popis: |
ion 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. |
| Databáze: |
OpenAIRE |
| Externí odkaz: |
|
