Skip to Main content Skip to Navigation
Journal articles

Social Learning in One-Arm Bandit Problems

Abstract : 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.
Complete list of metadatas
Contributor : Antoine Haldemann <>
Submitted on : Wednesday, March 17, 2010 - 3:43:20 PM
Last modification on : Tuesday, May 5, 2020 - 1:03:20 PM


  • HAL Id : hal-00464609, version 1


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



Record views