# Playing with and against Hedge

## TL;DR

This paper analyzes the worst-case performance of the Hedge algorithm in resource allocation problems modeled as multi-armed bandit full information games, with a focus on bounded total loss scenarios.

## Contribution

It provides a theoretical analysis of Hedge's worst-case performance when the total loss per round is bounded.

## Key findings

- Characterizes Hedge's worst-case performance bounds.
- Applies analysis to network and transportation resource problems.
- Highlights limitations of Hedge under bounded loss conditions.

## Abstract

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.