Stochastic Graph Bandit Learning with Side-Observations

TL;DR

This paper introduces a novel algorithm for stochastic contextual bandits with graph feedback that adapts to graph structures and reward gaps, providing improved regret bounds without needing prior graph information.

Contribution

The paper presents the first gap-dependent upper bound algorithm for stochastic graph bandits that adapts to graph structures and reward gaps, improving upon previous methods.

Findings

Achieves improved regret upper bounds.

Demonstrates computational efficiency through experiments.

Effectively adapts to graph structures and reward gaps.

Abstract

In this paper, we investigate the stochastic contextual bandit with general function space and graph feedback. We propose an algorithm that addresses this problem by adapting to both the underlying graph structures and reward gaps. To the best of our knowledge, our algorithm is the first to provide a gap-dependent upper bound in this stochastic setting, bridging the research gap left by the work in [35]. In comparison to [31,33,35], our method offers improved regret upper bounds and does not require knowledge of graphical quantities. We conduct numerical experiments to demonstrate the computational efficiency and effectiveness of our approach in terms of regret upper bounds. These findings highlight the significance of our algorithm in advancing the field of stochastic contextual bandits with graph feedback, opening up avenues for practical applications in various domains.