Matthew S. Hankins | Searcharxiv

arXiv2025

Nash Equilibrium Learning In Large Populations With First-Order Payoff Modifications

We establish Nash equilibrium learning in large populations of noncooperative, strategic agents. Our analysis considers the broadest class to date of payoff mechanisms with first-order modifications, capable of modeling bounded rationality and anticipatory effects, averaging, or Padé delay approximations. We propose a framework that, for the first time, combines two nonstandard system-theoretic passivity notions. Our results hold for discontinuous best response dynamics alongside continuous learning rules, significantly extending prior work.

eess.SY↗

arXiv2024

Counterclockwise Dissipativity, Potential Games and Evolutionary Nash Equilibrium Learning

We use system-theoretic passivity methods to study evolutionary Nash equilibria learning in large populations of agents engaged in strategic, non-cooperative interactions. The agents follow learning rules (rules for short) that capture their strategic preferences and a payoff mechanism ascribes payoffs to the available strategies. The population's aggregate strategic profile is the state of an associated evolutionary dynamical system. Evolutionary Nash equilibrium learning refers to the convergence of this state to the Nash equilibria set of the payoff mechanism. Most approaches consider memoryless payoff mechanisms, such as potential games. Recently, methods using $δ$-passivity and equilibrium independent passivity (EIP) have introduced dynamic payoff mechanisms. However, $δ$-passivity does not hold when agents follow rules exhibiting ``imitation" behavior, such as in replicator dynamics. Conversely, EIP applies to the replicator dynamics but not to $δ$-passive rules. We address this gap using counterclockwise dissipativity (CCW). First, we prove that continuous memoryless payoff mechanisms are CCW if and only if they are potential games. Subsequently, under (possibly dynamic) CCW payoff mechanisms, we establish evolutionary Nash equilibrium learning for any rule within a convex cone spanned by imitation rules and continuous $δ$-passive rules.

cs.GT↗