Fair Algorithms with Probing for Multi-Agent Multi-Armed Bandits

TL;DR

This paper introduces a novel framework for fair multi-agent multi-armed bandits that uses strategic probing to improve fairness and efficiency, with proven theoretical guarantees and strong empirical results.

Contribution

It presents a new probing-based approach for fairness in MA-MABs, including algorithms with theoretical performance bounds and practical effectiveness.

Findings

Outperforms baseline methods in fairness and efficiency

Achieves sublinear regret in online settings

Provides provable guarantees in offline scenarios

Abstract

We propose a multi-agent multi-armed bandit (MA-MAB) framework aimed at ensuring fair outcomes across agents while maximizing overall system performance. A key challenge in this setting is decision-making under limited information about arm rewards. To address this, we introduce a novel probing framework that strategically gathers information about selected arms before allocation. In the offline setting, where reward distributions are known, we leverage submodular properties to design a greedy probing algorithm with a provable performance bound. For the more complex online setting, we develop an algorithm that achieves sublinear regret while maintaining fairness. Extensive experiments on synthetic and real-world datasets show that our approach outperforms baseline methods, achieving better fairness and efficiency.