Social Learning in One-Arm Bandit Problems - Archive ouverte HAL Access content directly
Journal Articles Econometrica Year : 2007

Social Learning in One-Arm Bandit Problems

(1) , (2) , (3)
1
2
3
Eilon Solan
  • Function : Author
  • PersonId : 858141

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.
Not file

Dates and versions

hal-00464609 , version 1 (17-03-2010)

Identifiers

  • HAL Id : hal-00464609 , version 1

Cite

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

Share

Gmail Facebook Twitter LinkedIn More