The effect of population heterogeneity in multi-agent learning is practically relevant but remains far from being well-understood. Motivated by this, we introduce a model of multi-population learning that allows for heterogeneous beliefs within each population and where agents respond to their beliefs via smooth fictitious play (SFP).We show that the system state -- a probability distribution over beliefs -- evolves according to a system of partial differential equations akin to the continuity equations that commonly desccribe transport phenomena in physical systems. We establish the convergence of SFP to Quantal Response Equilibria in different classes of games capturing both network competition as well as network coordination. We also prove that the beliefs will eventually homogenize in all network games. Although the initial belief heterogeneity disappears in the limit, we show that it plays a crucial role for equilibrium selection in the case of coordination games as it helps select highly desirable equilibria. Contrary, in the case of network competition, the resulting limit behavior is independent of the initialization of beliefs, even when the underlying game has many distinct Nash equilibria.
翻译:多试剂学习中的人口差异效应实际上具有相关性,但远未完全理解。为此,我们引入了多人口学习模式,允许每个人群中的不同信仰,让代理者通过平滑的虚构游戏(SFP)回应他们的信仰。我们显示,系统状态 -- -- 一种比信仰的概率分布 -- -- 正在根据一个局部差异方程式的系统演变,类似于物理系统中常见的消除运输现象的连续性方程式。我们建立了SFP与不同类别游戏的横向反应平衡的趋同,捕捉网络竞争和网络协调。我们还证明,这些信仰最终将在所有网络游戏中实现同质化。虽然最初的信仰差异性在极限中消失,但我们表明,在协调游戏中,它对于平衡选择平衡性起着关键作用,因为它有助于选择非常可取的平衡性。相反,在网络竞争中,由此产生的限制行为是独立于信仰初始化的,即使基本游戏有许多不同的纳什平衡性。