Deutsch
 
Hilfe Datenschutzhinweis Impressum
  DetailsucheBrowse

Datensatz

DATENSATZ AKTIONENEXPORT
  Adaptive information-theoretic bounded rational decision-making with parametric priors

Grau-Moya, J., & Braun, D. (2015). Adaptive information-theoretic bounded rational decision-making with parametric priors. In NIPS 2015 Workshop on Bounded Optimality and Rational Metareasoning.

Item is

Externe Referenzen

einblenden:
ausblenden:
Beschreibung:
-
OA-Status:
Keine Angabe

Urheber

einblenden:
ausblenden:
 Urheber:
Grau-Moya, J1, Autor           
Braun, DA1, Autor           
Affiliations:
1Research Group Sensorimotor Learning and Decision-Making, Max Planck Institute for Biological Cybernetics, Max Planck Society, ou_1497809              

Inhalt

einblenden:
ausblenden:
Schlagwörter: -
 Zusammenfassung: Deviations from rational decision-making due to limited computational resources have been studied in the field of bounded rationality, originally proposed by Herbert Simon. There have been a number of different approaches to model bounded rationality ranging from optimality principles to heuristics. Here we take an information-theoretic approach to bounded rationality, where information-processing costs are measured by the relative entropy between a posterior decision strategy and a given fixed prior strategy. In the case of multiple environments, it can be shown that there is an optimal prior rendering the bounded rationality problem equivalent to the rate distortion problem for lossy compression in information theory. Accordingly, the optimal prior and posterior strategies can be computed by the well-known Blahut-Arimoto algorithm which requires the computation of partition sums over all possible outcomes and cannot be applied straightforwardly to continuous problems. Here we derive a sampling-based alternative update rule for the adaptation of prior behaviors of decision-makers and we show convergence to the optimal prior predicted by rate distortion theory. Importantly, the update rule avoids typical infeasible operations such as the computation of partition sums. We show in simulations a proof of concept for discrete action and environment domains. This approach is not only interesting as a generic computational method, but might also provide a more realistic model of human decision-making processes occurring on a fast and a slow time scale.

Details

einblenden:
ausblenden:
Sprache(n):
 Datum: 2015-12
 Publikationsstatus: Erschienen
 Seiten: -
 Ort, Verlag, Ausgabe: -
 Inhaltsverzeichnis: -
 Art der Begutachtung: -
 Identifikatoren: BibTex Citekey: GrauMoyaB2015
 Art des Abschluß: -

Veranstaltung

einblenden:
ausblenden:
Titel: NIPS 2015 Workshop on Bounded Optimality and Rational Metareasoning
Veranstaltungsort: Montreal, Canada
Start-/Enddatum: 2015-12-11

Entscheidung

einblenden:

Projektinformation

einblenden:

Quelle 1

einblenden:
ausblenden:
Titel: NIPS 2015 Workshop on Bounded Optimality and Rational Metareasoning
Genre der Quelle: Konferenzband
 Urheber:
Affiliations:
Ort, Verlag, Ausgabe: -
Seiten: 4 Band / Heft: - Artikelnummer: - Start- / Endseite: - Identifikator: -