PPAD-Complete Pure Approximate Nash Equilibria in Lipschitz Games

TL;DR

This paper proves that finding pure approximate Nash equilibria in Lipschitz games is PPAD-complete, establishing computational hardness and providing a method for deterministic equilibrium selection.

Contribution

It presents the first PPAD-completeness result for pure approximate equilibria in Lipschitz games and introduces a derandomization technique for equilibrium selection.

Findings

PPAD-completeness of pure approximate Nash equilibria in Lipschitz games.

A reduction from unrestricted polymatrix games demonstrating hardness.

A derandomization approach for equilibrium selection in Lipschitz games.

Abstract

Lipschitz games, in which there is a limit $\lambda$ (the Lipschitz value of the game) on how much a player's payoffs may change when some other player deviates, were introduced about 10 years ago by Azrieli and Shmaya. They showed via the probabilistic method that $n$-player Lipschitz games with $m$ strategies per player have pure $\epsilon$-approximate Nash equilibria, for $\epsilon\geq\lambda\sqrt{8n\log(2mn)}$. Here we provide the first hardness result for the corresponding computational problem, showing that even for a simple class of Lipschitz games (Lipschitz polymatrix games), finding pure $\epsilon$-approximate equilibria is PPAD-complete, for suitable pairs of values $(\epsilon(n), \lambda(n))$. Novel features of this result include both the proof of PPAD hardness (in which we apply a population game reduction from unrestricted polymatrix games) and the proof of containment in PPAD (by derandomizing the selection of a pure equilibrium from a mixed one). In fact, our approach implies containment in PPAD for any class of Lipschitz games where payoffs from mixed-strategy profiles can be deterministically computed.