A two armed bandit type problem revisited
ESAIM: Probability and Statistics, Volume 9  (2005), p. 277-282

In Benaïm and Ben Arous (2003) is solved a multi-armed bandit problem arising in the theory of learning in games. We propose a short and elementary proof of this result based on a variant of the Kronecker lemma.

DOI : https://doi.org/10.1051/ps:2005017
Classification:  91A20,  91A12,  60F99
Keywords: two-armed bandit problem, Kronecker lemma, learning theory, stochastic fictitious play
@article{PS_2005__9__277_0,
     author = {Pag\`es, Gilles},
     title = {A two armed bandit type problem revisited},
     journal = {ESAIM: Probability and Statistics},
     publisher = {EDP-Sciences},
     volume = {9},
     year = {2005},
     pages = {277-282},
     doi = {10.1051/ps:2005017},
     zbl = {1136.91327},
     mrnumber = {2174870},
     language = {en},
     url = {http://www.numdam.org/item/PS_2005__9__277_0}
}
Pagès, Gilles. A two armed bandit type problem revisited. ESAIM: Probability and Statistics, Volume 9 (2005) , pp. 277-282. doi : 10.1051/ps:2005017. http://www.numdam.org/item/PS_2005__9__277_0/

[1] M. Benaïm, Dynamics of stochastic algorithms, in Séminaire de probabilités XXXIII, J. Azéma et al. Eds., Springer-Verlag, Berlin. Lect. Notes Math. 1708 (1999) 1-68. | Numdam | Zbl 0955.62085

[2] M. Benaïm and G. Ben Arous, A two armed bandit type problem. Game Theory 32 (2003) 3-16. | Zbl 1101.91306