Censored Semi-Bandits for Resource Allocation
This work addresses resource allocation challenges in sequential decision-making, but it is incremental as it builds on existing bandit frameworks.
The paper tackles the problem of resource allocation in a censored semi-bandits setup, where the goal is to minimize expected loss by learning arm-specific thresholds and loss distributions, and it shows that the proposed algorithms achieve performance guarantees validated on synthetic data.
We consider the problem of sequentially allocating resources in a censored semi-bandits setup, where the learner allocates resources at each step to the arms and observes loss. The loss depends on two hidden parameters, one specific to the arm but independent of the resource allocation, and the other depends on the allocated resource. More specifically, the loss equals zero for an arm if the resource allocated to it exceeds a constant (but unknown) arm dependent threshold. The goal is to learn a resource allocation that minimizes the expected loss. The problem is challenging because the loss distribution and threshold value of each arm are unknown. We study this setting by establishing its `equivalence' to Multiple-Play Multi-Armed Bandits (MP-MAB) and Combinatorial Semi-Bandits. Exploiting these equivalences, we derive optimal algorithms for our problem setting using known algorithms for MP-MAB and Combinatorial Semi-Bandits. The experiments on synthetically generated data validate the performance guarantees of the proposed algorithms.