Nash Equilibrium Learning In Large Populations With First Order Payoff Modifications

We establish Nash equilibrium learning -- convergence of the population state to a suitably defined Nash equilibria set -- for a class of payoff dynamical mechanism with a first order modification. The first order payoff modification can model aspects of the agents' bounded rationality, anticipatory or averaging terms in the payoff mechanism, or first order Padé approximations of delays. To obtain our main results, we apply a combination of two nonstandard system-theoretic passivity notions.