Deutsch
 
Hilfe Datenschutzhinweis Impressum
  DetailsucheBrowse

Datensatz

DATENSATZ AKTIONENEXPORT
 
 
DownloadE-Mail
 Lokale TagsFreigabegeschichteDetailsÜbersicht
  A conversion between utility and information

Ortega, P., & Braun, D. (2010). A conversion between utility and information. In E. Hutter, & M. Kitzelmann (Eds.), Third Conference on Artificial General Intelligence (AGI 2010) (pp. 115-120). Amsterdam, Netherlands: Atlantis Press.

Item is

 

einblenden: alle ausblenden: alle

Basisdaten

einblenden: ausblenden:
Datensatz-Permalink: https://hdl.handle.net/11858/00-001M-0000-0013-C104-6 Versions-Permalink: https://hdl.handle.net/21.11116/0000-0002-94CF-E
Genre: Konferenzbeitrag

Externe Referenzen

einblenden:
ausblenden:
externe Referenz:
https://arxiv.org/pdf/0911.5106.pdf (beliebiger Volltext)
Beschreibung:
-
OA-Status:

Urheber

einblenden:
ausblenden:
 Urheber:
Ortega, PA1, Autor           
Braun, DA1, Autor           
Affiliations:
1University of Cambridge, ou_persistent22              

Inhalt

einblenden:
ausblenden:
Schlagwörter: -
 Zusammenfassung: Rewards typically express desirabilities or preferences over a set of alternatives. Here we propose that rewards can be defined for any probability distribution based on three desiderata, namely that rewards should be real-valued, additive and order-preserving, where the latter implies that more probable events should also be more desirable. Our main result states that rewards are then uniquely determined by the negative information content. To analyze stochastic processes, we define the utility of a realization as its reward rate. Under this interpretation, we show that the expected utility of a stochastic process is its negative entropy rate. Furthermore, we apply our results to analyze agent-environment interactions. We show that the expected utility that will actually be achieved by the agent is given by the negative cross-entropy from the input-output (I/O) distribution of the coupled interaction system and the agent's I/O distribution. Thus, our results allow for an information-theoretic interpretation of the notion of utility and the characterization of agent-environment interactions in terms of entropy dynamics.

Details

einblenden:
ausblenden:
Sprache(n):
 Datum: 2010-03
 Publikationsstatus: Erschienen
 Seiten: -
 Ort, Verlag, Ausgabe: -
 Inhaltsverzeichnis: -
 Art der Begutachtung: -
 Identifikatoren: BibTex Citekey: OrtegaB2010_2
 Art des Abschluß: -

Veranstaltung

einblenden:
ausblenden:
Titel: Third Conference on Artificial General Intelligence (AGI 2010)
Veranstaltungsort: Lugano, Switzerland
Start-/Enddatum: 2010-03-05 - 2010-03-08

Entscheidung

einblenden:

Projektinformation

einblenden:

Quelle 1

einblenden:
ausblenden:
Titel: Third Conference on Artificial General Intelligence (AGI 2010)
Genre der Quelle: Konferenzband
 Urheber:
Hutter, E, Herausgeber
Kitzelmann, M, Herausgeber
Affiliations:
-
Ort, Verlag, Ausgabe: Amsterdam, Netherlands : Atlantis Press
Seiten: - Band / Heft: - Artikelnummer: - Start- / Endseite: 115 - 120 Identifikator: ISBN: 978-90-78677-36-9