Better Regularization for Sequential Decision Spaces: The Dilatable Global Entropy Is a -Strongly Convex DGF on the Sequence-Form Polytope with Range at Most Research Paper
Two-player zero-sum extensive-form games (poker, negotiation, security games) are solved at scale by first-order methods. Writing each player's strategy in sequence form turns the computation of a Nash equilibrium into a bilinear saddle-point problem over two polytopes, and methods such as Nesterov's…