A Marriage between Adversarial Team Games and 2-player Games: Enabling Abstractions, No-regret Learning, and Subgame Solving

Ex ante correlation is becoming the mainstream approach for sequential adversarial team games,where a team of players faces another team in a zero-sum game. It is known that team members’asymmetric information makes both equilibrium computation APX-hard and team’s strategies not directly representable on the game tree. This latter issue prevents the adoption of successful tools for huge 2-player zero-sum games such as, e.g., abstractions, no-regret learning, and sub game solving. This work shows that we can re cover from this weakness by bridging the gap be tween sequential adversarial team games and 2-player games. In particular, we propose a new,suitable game representation that we call team public-information, in which a team is repre sented as a single coordinator who only knows information common to the whole team and pre scribes to each member an action for any pos sible private state. The resulting representation is highly explainable, being a 2-player tree in which the team’s strategies are behavioral with a direct interpretation and more expressive than he original extensive form when designing ab stractions. Furthermore, we prove payoff equiva lence of our representation, and we provide tech niques that, starting directly from the extensive form, generate dramatically more compact repre sentations without information loss. Finally, we experimentally evaluate our techniques when ap plied to a standard testbed, comparing their per formance with the current state of the art.