Strategic experimentation with Poisson bandits

Theoretical Economics

Volumn 5, Issue 2, 2010, Pages 275-311

  Keller, Godfrey ^a   Rady, Sven ^b  

^a UNIVERSITY OF OXFORD   (United Kingdom)

^b UNIVERSITY OF MUNICH   (Germany)

Author keywords

Bayesian learning; Differential difference equation; Markov perfect equilibrium; Piecewise deterministic process; Poisson process; Strategic experimentation; Two armed bandit

Indexed keywords

EID: 77955239646     PISSN: 19336837     EISSN: 15557561     Source Type: Journal    
DOI: 10.3982/TE595     Document Type: Article

References (18)

1. Bellman Richard, Cooke Kenneth L. Differential-Difference Equations 1963, Academic Press, New York
2. Bergemann Dirk, Välimäki Juuso. Bandit problems. The New Palgrave Dictionary of Economics 2008, Durlauf Steven N, Blume Larry E. Palgrave Macmillan, Basingstoke
3. Besanko David, Wu Jianjun. The impact of market structure and learning on the tradeoff between research competition and cooperation. 2008, Unpublished paper, School of Management, Northwestern University
4. Bolton Patrick, Harris Christopher. Strategic experimentation. Econometrica 1999, 67:349-374.
5. Bolton Patrick, Harris Christopher. Strategic experimentation: The undiscounted case. Incentives, Organization, and Public Economics 2000, 53-68. Hammond Peter J, Myles Gareth D. Oxford University Press, Oxford
6. Cohen Asaf, Solan Eilon. Bandit problems with Lévy payoff processes. 2009, http://arxiv.org/abs/0906.0835v1, Unpublished paper, Department of Statistics and Operations Research, Tel Aviv University, Available at
7. Davis Mark H A. Markov Models and Optimization 1993, Chapman & Hall, London
8. Décamps Jean-Paul, Mariotti Thomas. Investment timing and learning externalities. Journal of Economic Theory 2004, 118:80-102.
9. Hopenhayn Hugo, Squintani Francesco. Preemption games with private information. 2008, Unpublished paper, Department of Economics, University of Essex
10. Keller Godfrey, Rady Sven, Cripps Martin. Strategic experimentation with exponential bandits. Econometrica 2005, 73:39-68.
11. Klein Nicolas. Strategic learning in teams. 2010, Unpublished paper, Munich Graduate School of Economics
12. Klein Nicolas, Rady Sven. Negatively correlated bandits. 2008, Unpublished paper, University of Munich
13. Malueg David A, Tsutsui Shunichi O. Dynamic R&D competition with learning. RAND Journal of Economics 1997, 28:751-772.
14. Moscarini Giuseppe, Squintani Francesco. Competitive experimentation with private information: The survivor's curse. 2007, Unpublished paper, University of Essex
15. Presman Ernst L. Poisson version of the two-armed bandit problem with discounting. Theory of Probability and Its Applications 1990, 35:307-317.
16. Presman Ernst L, Sonin Isaac M. Sequential Control With Incomplete Information: The Bayesian Approach to Multi-Armed Bandit Problems 1990, Academic Press, London
17. Rothschild Michael. A two-armed bandit theory of market pricing. Journal of Economic Theory 1974, 9:185-202.
18. Strulovici Bruno. Learning while voting: Determinants of collective experimentation. Econometrica 2010, 78:933-971.