کد مقاله | کد نشریه | سال انتشار | مقاله انگلیسی | نسخه تمام متن |
---|---|---|---|---|
5071791 | 1477077 | 2013 | 22 صفحه PDF | دانلود رایگان |
- I analyze strategic experimentation with three-armed exponential bandits.
- Bandits have a safe arm and two risky arms whose types are negatively correlated.
- For perfect correlation, full efficiency is sustainable iff the stakes are high.
- For imperfect correlation, it is attainable for high stakes and initial optimism.
This paper analyzes a two-player game of strategic experimentation with three-armed exponential bandits in continuous time. Players play bandits of identical types, with one arm that is safe in that it generates a known payoff, whereas the likelihood of the risky armsʼ yielding a positive payoff is initially unknown. When the types of the two risky arms are perfectly negatively correlated, the efficient policy is an equilibrium if and only if the stakes are high enough. If the negative correlation is imperfect and stakes are high, there exists an equilibrium that leads to efficiency for optimistic enough prior beliefs.
Journal: Games and Economic Behavior - Volume 82, November 2013, Pages 636-657