On the Complexity of Nash Equilibria of Action-Graph Games

TL;DR

This paper investigates the computational complexity of finding Nash equilibria in action-graph games, providing efficient approximation algorithms for certain cases and proving hardness results for others.

Contribution

It introduces a Polynomial Time Approximation Scheme for AGGs with bounded treewidth and agent types, and establishes NP-hardness and PPAD-hardness results for more general cases.

Findings

PTAS exists for AGGs with constant treewidth and agent types

NP-completeness for pure-strategy Nash equilibrium existence in certain cases

PPAD-completeness for computing mixed Nash equilibria in general cases

Abstract

We consider the problem of computing Nash Equilibria of action-graph games (AGGs). AGGs, introduced by Bhat and Leyton-Brown, is a succinct representation of games that encapsulates both "local" dependencies as in graphical games, and partial indifference to other agents' identities as in anonymous games, which occur in many natural settings. This is achieved by specifying a graph on the set of actions, so that the payoff of an agent for selecting a strategy depends only on the number of agents playing each of the neighboring strategies in the action graph. We present a Polynomial Time Approximation Scheme for computing mixed Nash equilibria of AGGs with constant treewidth and a constant number of agent types (and an arbitrary number of strategies), together with hardness results for the cases when either the treewidth or the number of agent types is unconstrained. In particular, we show that even if the action graph is a tree, but the number of agent-types is unconstrained, it is NP-complete to decide the existence of a pure-strategy Nash equilibrium and PPAD-complete to compute a mixed Nash equilibrium (even an approximate one); similarly for symmetric AGGs (all agents belong to a single type), if we allow arbitrary treewidth. These hardness results suggest that, in some sense, our PTAS is as strong of a positive result as one can expect.