On the Complexity of Correlated Equilibria Beyond Normal-Form Games

2026-05-17

AI Summary

This work resolves a long-standing open problem regarding the computational complexity of correlated equilibria in extensive-form games, congestion games, and general concave games. By reducing the computation of correlated equilibria in concave quadratic games to the problem of finding a fixed point of a contraction mapping (Contr-hard), it establishes, for the first time, the computational hardness of this task and proves an exponential lower bound on swap regret. To circumvent this barrier, the paper introduces a tractable relaxation—Φ-equilibria—and presents the first fully polynomial-time approximation scheme (FPTAS). Leveraging contraction mappings and online learning techniques under the Mahalanobis norm, the proposed algorithm achieves efficient computation in time polynomial in both the dimension $d$ and $\log(1/\varepsilon)$.

Abstract

Correlated equilibria are a fundamental solution concept in game theory. However, despite decades of research, the complexity beyond games of polynomial type -- such as extensive-form games, congestion or routing games, and more broadly concave games -- has remained a major open problem, first highlighted by Papadimitriou and Roughgarden (JACM '08). In this paper, we resolve several long-standing questions concerning the complexity of correlated equilibria and swap regret minimization. First, we show that computing a correlated equilibrium in concave quadratic games is as hard as computing the fixed point of a contraction mapping (Contr), providing the first strong evidence of intractability. Moreover, we establish an unconditional, information-theoretic lower bound ruling out the existence of a strongly sublinear swap regret minimizer: any online learning algorithm requires exponentially many iterations in the dimension $d$ to guarantee at most $1/\text{poly}(d)$ (average) swap regret. To circumvent these hardness results, we examine the complexity of $Φ$-equilibria -- tractable relaxations of correlated equilibria. We obtain a fully polynomial-time approximation scheme (FPTAS) for computing poly-dimensional $Φ$-equilibria in general concave games. We complement this by showing that Contr-hardness persists even under poly-dimensional swap deviations in the regime where the precision $ε$ is exponentially small. Finally, we show that Contr-hardness can be bypassed in the canonical setting of concave \emph{quadratic games}, for which we provide a $\text{poly}(d, \log(1/ε))$-time algorithm for computing poly-dimensional $Φ$-equilibria. As a byproduct, we obtain an algorithm for computing fixed points of a mapping that is contracting with respect to an unknown Mahalanobis norm, which could be of independent interest.

Problem

• correlated equilibria
• computational complexity
• concave games
• extensive-form games
• swap regret

Innovation

• correlated equilibria
• computational complexity
• swap regret
• Φ-equilibria
• contraction mapping