Computing Nash equilibrium in bimatrix games is PPAD-hard, and many works have focused on the approximate solutions. When games are generated from a fixed unknown distribution, learning a Nash predictor via data-driven approaches can be preferable. In this paper, we study the learnability of approximate Nash equilibrium in bimatrix games. We prove that Lipschitz function class is agnostic Probably Approximately Correct (PAC) learnable with respect to Nash approximation loss. Additionally, to demonstrate the advantages of learning a Nash predictor, we develop a model that can efficiently approximate solutions for games under the same distribution. We show by experiments that the solutions from our Nash predictor can serve as effective initializing points for other Nash solvers.

翻译：电子计算比马特里克游戏中的纳什平衡是硬的,许多作品都集中在近似解决方案上。 当游戏由固定的未知分布生成时, 最好通过数据驱动的方法学习纳什预测器。 在本文中, 我们研究在双马特里克游戏中大约的纳什平衡的可学习性。 我们证明利普西茨函数类在纳什近似损失方面是不可知的, 很可能是正确( PAC ) 。 此外, 为了展示学习纳什预测器的好处, 我们开发了一种模型, 能够有效地将相同分布下的游戏解决方案相近。 我们通过实验发现, 我们的纳什预测器的解决方案可以作为其他纳什解答者的有效初始点。