arXiv Machine Learning By Ioannis Anagnostides, Constantinos Daskalakis, Gabriele Farina, Noah Golowich, Tuomas Sandholm, Brian Hu Zhang

Fixed Sets and the Hardness of Computing Correlated Equilibria

Read the original on arXiv Machine Learning →

The paper proves that computing an approximate correlated equilibrium for a polytope game is PPAD‑complete, showing it is polynomial‑time equivalent to finding a Nash equilibrium. It introduces the notion of a fixed set—a finite set contained in the convex hull of its image under a continuous function—and demonstrates that computing such a fixed set is PPAD‑hard even at inverse polynomial precision.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv Machine Learning
Oct 5

Normal-Form Correlation in Markov Games

arXiv:2610.03621v1 Announce Type: cross Abstract: There has been a surge of recent work on correlated equilibrium concepts in Markov games. However, existing results focus on concepts weaker than nor...

By Ioannis Anagnostides, Constantinos Daskalakis, Gabriele Farina, Noah Golowich, Tuomas Sandholm, Brian Hu Zhang
arXiv Machine Learning
Jul 14

Paradoxes of Game Theoretic Equilibria and Price of Anarchy

arXiv:2607. 11752v1 Announce Type: cross Abstract: For decades, static solution concepts (Nash, Correlated, and Coarse Correlated Equilibria) and the Price of Anarchy (PoA) have formed the bedrock of algorithmic game theory, with no-regret learning proving fast convergence to such game-theoretic equilibria.

By Georgios Piliouras, Ian Gemp, Siqi Liu, Luke Marris
Hugging Face Trending Papers
Jul 13

Paradoxes of Game Theoretic Equilibria and Price of Anarchy

For decades, static solution concepts (Nash, Correlated, and Coarse Correlated Equilibria) and the Price of Anarchy (PoA) have formed the bedrock of algorithmic game theory, with no-regret learning proving fast convergence to such game-theoretic equilibria. We show that reducing multi-agent learning to static equilibrium and black-box regret analysis obscures underlying dynamic disequilibrium and game theoretic bounds.