Solution concepts such as Nash Equilibria, Correlated Equilibria, and Coarse Correlated Equilibria are useful components for many multiagent machine learning algorithms. Unfortunately, solving a normal-form game could take prohibitive or non-deterministic time to converge, and could fail. We introduce the Neural Equilibrium Solver which utilizes a special equivariant neural network architecture to approximately solve the space of all games of fixed shape, buying speed and determinism. We define a flexible equilibrium selection framework, that is capable of uniquely selecting an equilibrium that minimizes relative entropy, or maximizes welfare. The network is trained without needing to generate any supervised training data. We show remarkable zero-shot generalization to larger games. We argue that such a network is a powerful component for many possible multiagent algorithms.

我们引入了神经均衡求解器，它利用特殊的等变神经网络体系结构来近似解决具有固定形状、购买速度和决定性的所有游戏空间，并定义了一个灵活的均衡选择框架，该框架能够唯一选择最小化相对熵或最大化福利的均衡，该网络的训练无需生成任何监督训练数据，展示了在更大的游戏中惊人的零样本泛化能力。这样的网络是许多可能的多主体算法的强大组成部分。

涡轮增压解决方案概念：用神经平衡器求解NE、CE和CCE