Optimal Exploration-Exploitation in a Multi-Armed-Bandit Problem with Non-stationary Rewards

TL;DR

This paper investigates the optimal balance of exploration and exploitation in non-stationary multi-armed bandit problems, providing a theoretical characterization of regret depending on reward variability.

Contribution

It introduces a framework that links reward variation to regret bounds, bridging stochastic and adversarial bandit theories.

Findings

Characterizes regret as a function of reward variation.

Establishes a connection between stochastic and adversarial bandit frameworks.

Provides a mathematical foundation for non-stationary reward analysis.

Abstract

In a multi-armed bandit (MAB) problem a gambler needs to choose at each round of play one of K arms, each characterized by an unknown reward distribution. Reward realizations are only observed when an arm is selected, and the gambler's objective is to maximize his cumulative expected earnings over some given horizon of play T. To do this, the gambler needs to acquire information about arms (exploration) while simultaneously optimizing immediate rewards (exploitation); the price paid due to this trade off is often referred to as the regret, and the main question is how small can this price be as a function of the horizon length T. This problem has been studied extensively when the reward distributions do not change over time; an assumption that supports a sharp characterization of the regret, yet is often violated in practical settings. In this paper, we focus on a MAB formulation which allows for a broad range of temporal uncertainties in the rewards, while still maintaining mathematical tractability. We fully characterize the (regret) complexity of this class of MAB problems by establishing a direct link between the extent of allowable reward "variation" and the minimal achievable regret. Our analysis draws some connections between two rather disparate strands of literature: the adversarial and the stochastic MAB frameworks.