Robust Multi-Agent Decision-Making in Finite-Population Games

TL;DR

This paper analyzes the robustness of a decision-making model in finite-population games, focusing on how parameter tuning can mitigate noise and inaccuracies, supported by theoretical and simulation results.

Contribution

It provides a detailed analysis of the KLD-RL model's robustness to noise and inaccuracies, offering practical guidelines for parameter tuning in population games.

Findings

Optimal parameter settings improve robustness against noise.

Simulation results validate theoretical insights.

Guidelines for practical parameter tuning are proposed.

Abstract

We study the robustness of an agent decision-making model in finite-population games, with a particular focus on the Kullback-Leibler Divergence Regularized Learning (KLD-RL) model. Specifically, we examine how the model's parameters influence the impact of various sources of noise and modeling inaccuracies -- factors commonly encountered in engineering applications of population games -- on agents' decision-making. Our analysis provides insights into how these parameters can be effectively tuned to mitigate such effects. Theoretical results are supported by numerical examples and simulation studies that validate the analysis and illustrate practical strategies for parameter selection.