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.

翻译：解概念如纳什均衡、相关均衡和粗相关均衡是多智能体机器学习算法中的重要组成部分。然而，求解标准型博弈可能耗费难以预测或非确定性时间才能收敛，甚至可能失败。我们提出神经均衡求解器，利用一种特殊的等变神经网络架构来近似求解所有固定形状的博弈空间，从而提升速度与确定性。我们定义了一个灵活的均衡选择框架，能够唯一地选择最小化相对熵或最大化社会福利的均衡。该网络无需生成任何监督训练数据即可完成训练。我们展示了其对更大规模博弈的显著零样本泛化能力。我们认为，此类网络可成为众多多智能体算法中的强大组件。