C. Bouton, Approximation gaussienne d'algorithmes stochastiquesàstochastiquesà dynamique markovienne, Probab. Stat, vol.24, issue.1, pp.131-155, 1988.

O. Brandì-ere and M. Duflo, Les algorithmes stochastiques contournent-ils lespì eges ?, Ann. Inst. H. Poincaré Probab. Statist, vol.32, pp.395-427, 1996.

J. C. Fort and G. Pagès, Decreasing step Stochastic algorithms: a.s. behaviour of weighted empirical measures, Monte Carlo Methods and Applications, vol.8, issue.3, pp.221-320, 2002.
DOI : 10.1515/mcma.2002.8.3.237

P. Hall and C. Heyde, Martingale Limit Theory and its Application, p.308, 1980.

H. J. Kushner and G. G. Yin, Stochastic approximation and recursive algorithms and applications, 2003.

D. Lamberton, G. Pagès, and P. Tarrès, When can the two-armed bandit algorithm be trusted?, Annals of Applied Probability, vol.14, issue.3, pp.1424-1454, 2004.
URL : https://hal.archives-ouvertes.fr/hal-00102253

D. Lamberton and G. Pagès, A penalized bandit algorithm, pre-print LPMA 1019, Univ. Paris 6, and pre-print Univ, 2005.
DOI : 10.1214/ejp.v13-489
URL : http://arxiv.org/abs/math/0510384

V. A. Lazarev, Convergence of stochastic approximation procedures in the case of a regression equation with several roots, transl. from) Problemy Pederachi Informatsii, 1992.

K. S. Narendra and M. A. Thathachar, Learning Automata - A Survey, IEEE Transactions on Systems, Man, and Cybernetics, vol.4, issue.4, pp.323-334, 1974.
DOI : 10.1109/TSMC.1974.5408453

K. S. Narendra and M. A. Thathachar, Learning Automata -An introduction, p.476, 1989.

M. Pelletier, Weak convergence rates for stochastic approximation with application to multiple targets and simulated annealing, The Annals of Applied Probability, vol.8, issue.1, pp.10-44, 1998.
DOI : 10.1214/aoap/1027961032

R. Pemantle, Nonconvergence to Unstable Points in Urn Models and Stochastic Approximations, The Annals of Probability, vol.18, issue.2, pp.698-712, 1990.
DOI : 10.1214/aop/1176990853