Playing with and against Hedge
This is an incremental theoretical analysis for researchers in optimization and network resource management.
The paper analyzes the worst-case performance of the Hedge algorithm in multi-armed bandit problems with bounded per-round losses, focusing on applications in networks and transportation.
Hedge has been proposed as an adaptive scheme, which guides an agent's decision in resource selection and distribution problems that can be modeled as a multi-armed bandit full information game. Such problems are encountered in the areas of computer and communication networks, e.g. network path selection, load distribution, network interdiction, and also in problems in the area of transportation. We study Hedge under the assumption that the total loss that can be suffered by the player in each round is upper bounded. In this paper, we study the worst performance of Hedge.