Satisficing in Multi-Armed Bandit Problems

Satisficing is a relaxation of maximizing and allows for less risky decision making in the face of uncertainty. We propose two sets of satisficing objectives for the multi-armed bandit problem, where the objective is to achieve reward-based decision-making performance above a given threshold. We sho...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	IEEE transactions on automatic control 2017-08, Vol.62 (8), p.3788-3803
Hauptverfasser:	Reverdy, Paul, Srivastava, Vaibhav, Leonard, Naomi Ehrich
Format:	Artikel
Sprache:	eng
Schlagworte:	Algorithm design and analysis Context Decision making Face Linear programming Multi-armed bandit Robustness upper credible limit (UCL)
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!