Heterogeneous Explore-Exploit Strategies on Multi-Star Networks

TL;DR

This paper explores how heterogeneity in explore-exploit strategies among agents in multi-star networks can enhance group performance, providing theoretical analysis and simulations to validate the benefits over homogeneous strategies.

Contribution

The paper introduces and analyzes novel heterogeneous explore-exploit strategies tailored for multi-star networks, demonstrating improved group rewards over homogeneous approaches.

Findings

Heterogeneous strategies outperform homogeneous ones in irregular networks.

Center agents exploring more benefits peripheral agents' data collection.

Theoretical guarantees confirm performance improvements.

Abstract

We investigate the benefits of heterogeneity in multi-agent explore-exploit decision making where the goal of the agents is to maximize cumulative group reward. To do so we study a class of distributed stochastic bandit problems in which agents communicate over a multi-star network and make sequential choices among options in the same uncertain environment. Typically, in multi-agent bandit problems, agents use homogeneous decision-making strategies. However, group performance can be improved by incorporating heterogeneity into the choices agents make, especially when the network graph is irregular, i.e. when agents have different numbers of neighbors. We design and analyze new heterogeneous explore-exploit strategies, using the multi-star as the model irregular network graph. The key idea is to enable center agents to do more exploring than they would do using the homogeneous strategy, as a means of providing more useful data to the peripheral agents. In the case all agents broadcast their reward values and choices to their neighbors with the same probability, we provide theoretical guarantees that group performance improves under the proposed heterogeneous strategies as compared to under homogeneous strategies. We use numerical simulations to illustrate our results and to validate our theoretical bounds.