Evolutionary Game Theory Squared: Evolving Agents in Endogenously Evolving Zero-Sum Games

TL;DR

This paper introduces a novel framework where both agents and zero-sum games evolve strategically over time, revealing regularities like conservation laws, recurrence, and convergence to Nash equilibrium despite chaotic coevolution.

Contribution

It develops a comprehensive theoretical analysis of coevolving agents and games, demonstrating regularities and providing an efficient algorithm for predicting long-term behavior.

Findings

System exhibits information-theoretic conservation laws

System is Poincaré recurrent with recurrent orbits

Time-average behavior converges to Nash equilibrium

Abstract

The predominant paradigm in evolutionary game theory and more generally online learning in games is based on a clear distinction between a population of dynamic agents that interact given a fixed, static game. In this paper, we move away from the artificial divide between dynamic agents and static games, to introduce and analyze a large class of competitive settings where both the agents and the games they play evolve strategically over time. We focus on arguably the most archetypal game-theoretic setting -- zero-sum games (as well as network generalizations) -- and the most studied evolutionary learning dynamic -- replicator, the continuous-time analogue of multiplicative weights. Populations of agents compete against each other in a zero-sum competition that itself evolves adversarially to the current population mixture. Remarkably, despite the chaotic coevolution of agents and games, we prove that the system exhibits a number of regularities. First, the system has conservation laws of an information-theoretic flavor that couple the behavior of all agents and games. Secondly, the system is Poincar\'{e} recurrent, with effectively all possible initializations of agents and games lying on recurrent orbits that come arbitrarily close to their initial conditions infinitely often. Thirdly, the time-average agent behavior and utility converge to the Nash equilibrium values of the time-average game. Finally, we provide a polynomial time algorithm to efficiently predict this time-average behavior for any such coevolving network game.