P. Auer, N. Cesa-bianchi, and P. Fischer, Finite-time analysis of the multiarmed bandit problem, Mach. Learn, vol.47, issue.2-3, p.235256, 2002.

J. Y. Audibert, R. Munos, and C. Szepesvári, Exploration-exploitation tradeo using variance estimates in multi-armed bandits, Theoretical Computer Science, issue.19, p.41018761902, 2009.

M. Aoyagi, Mutual Observability and the Convergence of Actions in a Multi-Person Two-Armed Bandit Model, Journal of Economic Theory, vol.82, issue.2, p.405424, 1998.
DOI : 10.1006/jeth.1995.2450

A. V. Banerjee, A Simple Model of Herd Behavior, The Quarterly Journal of Economics, vol.107, issue.3, p.797817, 1992.
DOI : 10.2307/2118364

P. Bolton and C. Harris, Strategic experimentation. Econmetrica, p.349374, 1999.

M. Brezzi and T. L. Lai, Optimal learning and experimentation in bandit problems, Journal of Economic Dynamics and Control, vol.27, issue.1, p.87108, 2002.
DOI : 10.1016/S0165-1889(01)00028-8

D. Bergemann and J. Välimäki, Market diusion with two-sided learning, The RAND Journal of Economics, p.773795, 1997.
DOI : 10.2307/2555786
URL : http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.305.342

]. B. Cam06 and . Camargo, Learning in society, Meeting Papers. Society for Economic Dynamics, 2006.

C. Chamley and D. Gale, Information Revelation and Strategic Delay in a Model of Investment, Econometrica, vol.62, issue.5, p.10651085, 1994.
DOI : 10.2307/2951507

J. [. Caplin and . Leahy, Business as usual, market crashes, and wisdom after the fact, The American Economic Review, p.548565, 1994.

Y. S. Chow and H. Robbins, On optimal stopping rules. Probability Theory and Related Fields, p.3349, 1963.
DOI : 10.1007/978-1-4612-5110-1_39

T. Ferguson, Optimal stopping and applications. preprint, Mathematics Department, 2006.

J. C. Gittins, Bandit processes and dynamic allocation indices, Journal of the Royal Statistical Society. Series B (Methodological), p.148177, 1979.
DOI : 10.1002/9780470980033

N. Klein and S. Rady, Negatively Correlated Bandits. Discussion Papers in Economics, 2008.

S. [. Keller, M. Rady, and . Cripps, Strategic Experimentation with Exponential Bandits, Econometrica, vol.73, issue.1, p.3968, 2005.
DOI : 10.1111/j.1468-0262.2005.00564.x

T. Lai and H. Robbins, Asymptotically ecient adaptive allocation rules, Advances in applied mathematics, vol.6, issue.1, p.422, 1985.

P. Murto and J. Välimäki, Learning in a Model of Exit, Helsinki Center of Economic Research Working Paper, vol.110, 2006.

E. [. Rosenberg, N. Solan, and . Vieille, Social Learning in OneArmed Bandit Problems, Econometrica, vol.75, p.15911611, 2007.

A. [. Rosenberg, N. Salomon, and . Vieille, On games of strategic experimentation, Games and Economic Behavior, vol.82, 2010.
DOI : 10.1016/j.geb.2013.06.006
URL : https://hal.archives-ouvertes.fr/hal-00579613