Meta-learning a regret minimizer to minimize correlation in coarse-correlated equilibria yields far better Nash equilibrium approximations in general-sum games than prior regret minimization techniques.
Combining local search techniques and path following for bimatrix games
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
Computing a Nash equilibrium (NE) is a central task in computer science. An NE is a particularly appropriate solution concept for two-agent settings because coalitional deviations are not an issue. However, even in this case, finding an NE is PPAD-complete. In this paper, we combine path following algorithms with local search techniques to design new algorithms for finding exact and approximate NEs. We show that our algorithms largely outperform the state of the art and that almost all the known benchmark game classes are easily solvable or approximable (except for the GAMUT CovariantGameRand class).
fields
cs.GT 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Approximating Nash Equilibria in General-Sum Games via Meta-Learning
Meta-learning a regret minimizer to minimize correlation in coarse-correlated equilibria yields far better Nash equilibrium approximations in general-sum games than prior regret minimization techniques.