We investigate an algorithm that assigns to any game in normal form an approximating game that admits an ordinal potential function. Due to the properties of potential games, the algorithm equips every game with a surrogate reward structure that allows efficient multi-agent learning. Numerical simulations using the replicator dynamics show that 'potentialization' guarantees convergence to stable agent behavior.

翻译：本文研究一种算法，该算法可为任意标准型博弈分配一个近似博弈，该近似博弈允许存在序数势函数。基于势博弈的特性，该算法为每个博弈提供了一种替代性奖励结构，从而支持高效的多智能体学习。利用复制者动力学的数值模拟表明，"势化"过程能够保证智能体行为收敛至稳定状态。