Pure Exploration for Constrained Best Mixed Arm Identification with a Fixed Budget
This addresses a pure exploration problem with cost constraints for decision-making under uncertainty, but it is incremental as it extends existing bandit frameworks to mixed arms with constraints.
The paper tackles the constrained best mixed arm identification problem in stochastic bandits, where the optimal solution may be a randomized mixture of arms, and proposes the SFSR algorithm, which achieves an error probability that decays exponentially with the budget N and problem-specific constants.
In this paper, we introduce the constrained best mixed arm identification (CBMAI) problem with a fixed budget. This is a pure exploration problem in a stochastic finite armed bandit model. Each arm is associated with a reward and multiple types of costs from unknown distributions. Unlike the unconstrained best arm identification problem, the optimal solution for the CBMAI problem may be a randomized mixture of multiple arms. The goal thus is to find the best mixed arm that maximizes the expected reward subject to constraints on the expected costs with a given learning budget $N$. We propose a novel, parameter-free algorithm, called the Score Function-based Successive Reject (SFSR) algorithm, that combines the classical successive reject framework with a novel score-function-based rejection criteria based on linear programming theory to identify the optimal support. We provide a theoretical upper bound on the mis-identification (of the the support of the best mixed arm) probability and show that it decays exponentially in the budget $N$ and some constants that characterize the hardness of the problem instance. We also develop an information theoretic lower bound on the error probability that shows that these constants appropriately characterize the problem difficulty. We validate this empirically on a number of average and hard instances.