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 :
10.1051/ps:2005017
Classification :
91A20, 91A12, 60F99
Mots-clés : two-armed bandit problem, Kronecker lemma, learning theory, stochastic fictitious play
Mots-clés : 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}, pages = {277--282}, publisher = {EDP-Sciences}, volume = {9}, year = {2005}, doi = {10.1051/ps:2005017}, mrnumber = {2174870}, zbl = {1136.91327}, language = {en}, url = {http://www.numdam.org/articles/10.1051/ps:2005017/} }
Pagès, Gilles. A two armed bandit type problem revisited. ESAIM: Probability and Statistics, Tome 9 (2005), pp. 277-282. doi : 10.1051/ps:2005017. http://www.numdam.org/articles/10.1051/ps:2005017/