3 papers
cs.AI2026
Steering Equilibrium Selection in Regularized Self-Play via the Reference Policy
Luis Leal
Regularized self-play -- the family behind DeepNash's Stratego play -- drives a two-player zero-sum policy to a Nash equilibrium by best-responding to a slowly moving, entropy-regu…
cs.AI2026
The Curvature Shadow: An Apparent Failure of Maximum-Entropy Equilibrium Selection is a Removable Artifact
Luis Leal
In two-player zero-sum games whose Nash equilibria form a convex set, regularized solvers such as Regularized Nash Dynamics (R-NaD) empirically select the maximum-entropy member: t…
cs.GT2026
Which Nash Equilibrium? Solver-Dependent Selection on Zero-Sum Nash Polytopes
Luis Leal
Many two-player zero-sum games admit not a unique Nash equilibrium but a convex set of them: a polytope of profiles that all share the minimax value V* yet prescribe different beha…