论文标题
涡轮增压溶液概念：用神经平衡求解器求解NE，CES和CCE
Turbocharging Solution Concepts: Solving NEs, CEs and CCEs with Neural Equilibrium Solvers
论文作者
论文摘要
解决方案概念（例如NASH平衡，相关平衡和粗相关平衡）是许多多种机器学习算法的有用组件。不幸的是，解决正常形式的游戏可能需要过度或非确定性的时间来融合，并且可能会失败。我们介绍了神经平衡求解器，该神经平衡求解器利用特殊的eprovariant神经网络架构来大致解决所有固定形状，购买速度和确定性的游戏空间。我们定义了一个灵活的平衡选择框架，该框架能够唯一选择最小化相对熵或最大化福利的平衡。该网络经过培训，无需生成任何监督培训数据。我们对较大的游戏表现出了显着的零拍打概括。我们认为，这种网络是许多可能的多基因算法的强大组件。
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.
