Bandit Algorithms

(Jeff_L) #1
20.4 Exercises 250

The quantities pθ′(Xs)/pθ(Xs) are calledlikelihood ratios. That the
product of likelihood ratios forms a martingale is a cornerstone result of
classical parametric statistics. The sequential form that appears in the above
exercise is based on Lemma 2 of Lai and Robbins [1985] who cite Robbins
and Siegmund [1972] as the original source.

Free download pdf