论文标题
交替交替的人群和控制神经网络以解决高维的随机均值游戏
Alternating the Population and Control Neural Networks to Solve High-Dimensional Stochastic Mean-Field Games
论文作者
论文摘要
我们提出Apac-Net，这是一种交替的人群和代理控制神经网络，用于解决随机平均野外游戏（MFGS）。我们的算法针对MFG的高维实例，这些实例是现有溶液方法无法实现的。我们通过两个步骤实现这一目标。首先，我们利用了MFGS表现出来的基本变分原始偶对偶的结构，并将其作为凸 - 孔侧鞍点问题。其次，我们分别通过两个神经网络参数化值和密度函数。通过以这种方式措辞，解决MFG可以解释为训练生成对抗网络（GAN）的特殊情况。我们展示了我们方法对多达100维MFG问题的潜力。
We present APAC-Net, an alternating population and agent control neural network for solving stochastic mean field games (MFGs). Our algorithm is geared toward high-dimensional instances of MFGs that are beyond reach with existing solution methods. We achieve this in two steps. First, we take advantage of the underlying variational primal-dual structure that MFGs exhibit and phrase it as a convex-concave saddle point problem. Second, we parameterize the value and density functions by two neural networks, respectively. By phrasing the problem in this manner, solving the MFG can be interpreted as a special case of training a generative adversarial network (GAN). We show the potential of our method on up to 100-dimensional MFG problems.
