Sparsity-Agnostic Lasso Bandit
Min-hwan Oh 1 Garud Iyengar 2 Assaf Zeevi 2
Abstract the traditional MAB problem, here pulling any one arm
provides some information about the unknown parameter
We consider a stochastic contextual bandit prob- vector, and hence, insight into the average reward of all the
lem where the dimension d of the feature vectors other arms. These contextual bandit algorithms ...


雷达卡




京公网安备 11010802022788号







