Tuomas Sandholm

Convergence of Regret Matching in Potential Games and Constrained Optimization

General search techniques without common knowledge for imperfect-information games, and application to superhuman Fog of War chess

Learning a Game by Paying the Agents

Decision Making under Imperfect Recall: Algorithms and Benchmarks

AlphaZeroES: Direct Score Maximization Can Outperform Planning Loss Minimization in Single-Agent Settings

Expected Variational Inequalities

The Complexity of Symmetric Equilibria in Min-Max Optimization and Team Zero-Sum Games