Strategic Learning in Teams
Nicolas A. Klein
University of Bonn - Institute of Economic Theory II
July 23, 2010
This paper analyzes a two-player game of strategic experimentation with three-armed exponential bandits in continuous time. Players face replica bandits, with one arm that is safe in that it generates a known payoff, whereas the likelihood of the risky arms' yielding a positive payoff is initially unknown. It is common knowledge that the types of the two risky arms are perfectly negatively correlated. I show that the efficient policy is incentive-compatible if, and only if, the stakes are high enough. Moreover, learning will be complete in any Markov perfect equilibrium with continuous value functions if, and only if, the stakes exceed a certain threshold.
Number of Pages in PDF File: 29
Keywords: Strategic Experimentation, Three-Armed Bandit, Exponential Distribution, Poisson Process, Bayesian Learning, Markov Perfect Equilibrium
JEL Classification: C73, D83, O32working papers series
Date posted: August 5, 2010 ; Last revised: March 4, 2011
© 2013 Social Science Electronic Publishing, Inc. All Rights Reserved.
This page was processed by apollo7 in 0.453 seconds