Abstract Policy-Space Response Oracles (PSRO) is an influential algorithm framework for
approximating a Nash Equilibrium (NE) in multi-agent non-transitive games. Many previous …

Game theory studies the mathematical models for self-interested individuals. Nash
equilibrium is arguably the most central solution in game theory. While finding the Nash …

In the course of playing or solving a game, it is common to face a series of changing other-
agent strategies. These strategies often share elements: the set of possible policies to play …

Learning in strategy games (eg StarCraft, poker) requires the discovery of diverse policies.
This is often achieved by iteratively training new policies against existing ones, growing a …

In this paper, we introduce a two-player zero-sum framework between a trainable\emph
{Solver} and a\emph {Data Generator} to improve the generalization ability of deep learning …

We study computationally efficient methods for finding equilibria in n-player general-sum
games, specifically ones that afford complex visuomotor skills. We show how existing …

Policy Space Response Oracle methods (PSRO) provide a general solution to learn Nash
equilibrium in two-player zero-sum games but suffer from two drawbacks:(1) the computation …

Game-based decision-making involves reasoning over both world dynamics and strategic
interactions among the agents. Typically, empirical models capturing these respective …

Policy-Space Response Oracles (PSRO) as a general algorithmic framework has achieved
state-of-the-art performance in learning equilibrium policies of two-player zero-sum games …

Intuitively, experience playing against one mixture of opponents in a given domain should
be relevant for a different mixture in the same domain. If the mixture changes, ideally we …