English

Passivity Tools for Hybrid Learning Rules in Large Populations

Dynamical Systems 2024-12-16 v3 Systems and Control Systems and Control Optimization and Control

Abstract

Recent work has pioneered the use of system-theoretic passivity to study equilibrium stability for the dynamics of noncooperative strategic interactions in large populations of learning agents. In this and related works, the stability analysis leverages knowledge that certain ``canonical'' classes of learning rules used to model the agents' strategic behaviors satisfy a passivity condition known as δ\delta-passivity. In this paper, we consider that agents exhibit learning behaviors that do not align with a canonical class. Specifically, we focus on characterizing δ\delta-passivity for hybrid learning rules that combine elements from canonical classes. Our analysis also introduces and uses a more general version of δ\delta-passivity, which, for the first time, can handle discontinuous learning rules, including those showing best-response behaviors. We state and prove theorems establishing δ\delta-passivity for two broad convex cones of hybrid learning rules. These cones can merge into a larger one preserving δ\delta-passivity in scenarios limited to two strategies. In our proofs, we establish intermediate facts that are significant on their own and could potentially be used to further generalize our work. We illustrate the applicability of our results through numerical examples.

Keywords

Cite

@article{arxiv.2407.02083,
  title  = {Passivity Tools for Hybrid Learning Rules in Large Populations},
  author = {Jair Certorio and Kevin Chang and Nuno C. Martins and Pierluigi Nuzzo and Yasser Shoukry},
  journal= {arXiv preprint arXiv:2407.02083},
  year   = {2024}
}

Comments

12 pages, 3 figures

R2 v1 2026-06-28T17:26:12.961Z