Strategic Learning in Teams
29 Pages Posted: 5 Aug 2010 Last revised: 4 Mar 2011
Date Written: July 23, 2010
Abstract
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.
Keywords: Strategic Experimentation, Three-Armed Bandit, Exponential Distribution, Poisson Process, Bayesian Learning, Markov Perfect Equilibrium
JEL Classification: C73, D83, O32
Suggested Citation: Suggested Citation
Do you have negative results from your research you’d like to share?
Recommended Papers
-
The Financing of Innovation: Learning and Stopping
By Dirk Bergemann and Ulrich Hege
-
Gradualism and Irreversibility
By Ben Lockwood and Jonathan Thomas
-
Strategic Experimentation with Exponential Bandits
By Martin Cripps, Godfrey Keller, ...
-
Strategic Experimentation with Exponential Bandits
By Martin Cripps, Godfrey Keller, ...
-
Strategic Experimentation with Poisson Bandits
By Godfrey Keller and Sven Rady
-
Strategic Experimentation with Poisson Bandits
By Godfrey Keller and Sven Rady
-
By Dirk Bergemann and Juuso Valimaki
-
Price Dispersion and Learning in a Dynamic Differentiated-Goods Duopoly
By Godfrey Keller and Sven Rady
-
On the Smoothness of Value Functions and the Existence of Optimal Strategies