Social Learning in One-Arm Bandit Problems

Nicolas Vieille (1) , Dinah Rosenberg (2) , Eilon Solan (3)

1 GREGH - Groupement de Recherche et d'Etudes en Gestion à HEC
2 LAGA - Laboratoire Analyse, Géométrie et Applications
3 TAU - Tel Aviv University

We study a two-player one-arm bandit problem in discrete time, in which the risky arm can have two possible types, high and low, the decision to stop experimenting is irreversible, and players observe each other's actions but not each other's payoffs. We prove that all equilibria are in cutoff strategies and provide several qualitative results on the sequence of cutoffs.

Mots clés: Social learning; One-arm bandit

Domaines: Economie et sciences de la décision

Nicolas Vieille, Dinah Rosenberg, Eilon Solan. Social Learning in One-Arm Bandit Problems. Econometrica, 2007, Vol.75,n°6, pp.1591-1611. ⟨hal-00464609⟩