文档介绍：MINIMAX R-STAGE STRATEGY FOR THE
MULTI-ARMED BANDIT PROBLEM
∗ ∗
∗ Novgorod State University, -Petersburgskaya str. 41,
Velikiy Novgorod, 173003, Russia,
Fax: +7 (8162) 62-41-10,
e-mail:Alexander.******@
******@
Abstract: The r-stage multi-armed bandit problem is considered in minimax
setting on the finite sufficiently large time interval T . A sequential control
procedure with a priori specified magnitudes of learning stages and thresholds
is offered. The value of the minimax risk close to T α with α = 2r−1/(2r − 1) is
obtained. The applications to information transmission and medical treatments
are discussed. Considered approach is especially valuable for systems with parallel
processing in which the number of stages r mainly influences the total duration of
the process. Copyright
c 2007 IFAC
Keywords: multi-armed bandit, adaptive learning control, adaptive choice of
alternatives, sequential decisions, minimax control, parallel processing
1.