Showing cs.AIShow all
2 papers · 1 filter
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…