Deutsch
 
Hilfe Datenschutzhinweis Impressum
  DetailsucheBrowse

Datensatz

DATENSATZ AKTIONENEXPORT
Zur Ablage hinzufügen
 DetailsÜbersicht
  Two steps to risk sensitivity

Gagne, C., & Dayan, P. (in press). Two steps to risk sensitivity. In M. Ranzato, A. Beygelzimer, P. Liang, J. Vaughan, & Y. Dauphin (Eds.), Advances in Neural Information Processing Systems 34.

Item is

 

einblenden: alle ausblenden: alle

Basisdaten

einblenden: ausblenden:
Datensatz-Permalink: https://hdl.handle.net/21.11116/0000-0009-8A1E-B Versions-Permalink: https://hdl.handle.net/21.11116/0000-0009-A6EE-0
Genre: Konferenzbeitrag

Externe Referenzen

einblenden:
ausblenden:
externe Referenz:
https://openreview.net/pdf?id=HnLDt9v6Q-j (beliebiger Volltext)
Beschreibung:
-
OA-Status:

Urheber

einblenden:
ausblenden:
 Urheber:
Gagne, C1, 2, Autor           
Dayan, P1, 2, Autor           
Affiliations:
1Department of Computational Neuroscience, Max Planck Institute for Biological Cybernetics, Max Planck Society, ou_3017468              
2Max Planck Institute for Biological Cybernetics, Max Planck Society, ou_1497794              

Inhalt

einblenden:
ausblenden:
Schlagwörter: -
 Zusammenfassung: Distributional reinforcement learning (RL) – in which agents learn about all the possible long-term consequences of their actions, and not just the expected value – is of great recent interest. One of the most important affordances of a distributional view is facilitating a modern, measured, approach to risk when outcomes are not completely certain. By contrast, psychological and neuroscientific investigations into decision making under risk have utilized a variety of more venerable theoretical models such as prospect theory that lack axiomatically desirable properties such as coherence. Here, we consider a particularly relevant risk measure for modeling human and animal planning, called conditional value-at-risk (CVaR), which quantifies worst-case outcomes (e.g., vehicle accidents or predation). We first adopt a conventional distributional approach to CVaR in a sequential setting and reanalyze the choices of human decision-makers in the well-known two-step task, revealing substantial risk aversion that had been lurking under stickiness and perseveration. We then consider a further critical property of risk sensitivity, namely time consistency, showing alternatives to this form of CVaR that enjoy this desirable characteristic. We use simulations to examine settings in which the various forms differ in ways that have implications for human and animal planning and behavior.

Details

einblenden:
ausblenden:
Sprache(n):
 Datum: 2021-10
 Publikationsstatus: Angenommen
 Seiten: -
 Ort, Verlag, Ausgabe: -
 Inhaltsverzeichnis: -
 Art der Begutachtung: -
 Identifikatoren: -
 Art des Abschluß: -

Veranstaltung

einblenden:
ausblenden:
Titel: Thirty-fifth Conference on Neural Information Processing Systems (NeurIPS 2021)
Veranstaltungsort: -
Start-/Enddatum: 2021-12-06 - 2021-12-14

Entscheidung

einblenden:

Projektinformation

einblenden:

Quelle 1

einblenden:
ausblenden:
Titel: Advances in Neural Information Processing Systems 34
Genre der Quelle: Konferenzband
 Urheber:
Ranzato, M, Herausgeber
Beygelzimer, A, Herausgeber
Liang, PS, Herausgeber
Vaughan, JW, Herausgeber
Dauphin, Y, Herausgeber
Affiliations:
-
Ort, Verlag, Ausgabe: -
Seiten: - Band / Heft: - Artikelnummer: - Start- / Endseite: - Identifikator: -