Asymptotically Optimal Multi-Armed Bandit Policies under a Cost Constraint
This addresses resource allocation under uncertainty for applications like clinical trials or online advertising, but it is incremental as it extends existing bandit theory with cost constraints.
The paper tackles the multi-armed bandit problem with a cost constraint, developing asymptotically optimal policies that minimize regret while adhering to the constraint, and provides explicit forms for Normal distributions.
We develop asymptotically optimal policies for the multi armed bandit (MAB), problem, under a cost constraint. This model is applicable in situations where each sample (or activation) from a population (bandit) incurs a known bandit dependent cost. Successive samples from each population are iid random variables with unknown distribution. The objective is to design a feasible policy for deciding from which population to sample from, so as to maximize the expected sum of outcomes of $n$ total samples or equivalently to minimize the regret due to lack on information on sample distributions, For this problem we consider the class of feasible uniformly fast (f-UF) convergent policies, that satisfy the cost constraint sample-path wise. We first establish a necessary asymptotic lower bound for the rate of increase of the regret function of f-UF policies. Then we construct a class of f-UF policies and provide conditions under which they are asymptotically optimal within the class of f-UF policies, achieving this asymptotic lower bound. At the end we provide the explicit form of such policies for the case in which the unknown distributions are Normal with unknown means and known variances.