Convex piecewise quadratic (PWQ) functions frequently appear in control and elsewhere. For instance, it is well-known that the optimal value function (OVF) as well as Q-functions for linear MPC are convex PWQ functions. Now, in learning-based control, these functions are often represented with the help of artificial neural networks (NN). In this context, a recurring question is how to choose the topology of the NN in terms of depth, width, and activations in order to enable efficient learning. An elegant answer to that question could be a topology that, in principle, allows to exactly describe the function to be learned. Such solutions are already available for related problems. In fact, suitable topologies are known for piecewise affine (PWA) functions that can, for example, reflect the optimal control law in linear MPC. Following this direction, we show in this paper that convex PWQ functions can be exactly described by max-out-NN with only one hidden layer and two neurons.
翻译:PWQ 函数通常出现在控制区和其他地方。 例如, 众所周知, 线性 MPC 的最佳值函数( OVF) 和 Q 函数都是 convex PWQ 函数。 现在, 在以学习为基础的控制中, 这些函数通常在人工神经网络( NN) 的帮助下被代表。 在此情况下, 一个反复出现的问题是, 如何从深度、 宽度和激活角度选择 NN 的地形学, 以便有效学习。 对这个问题的优雅回答可能是一种表层学, 原则上可以精确描述要学的函数。 这些解决方案已经可供相关问题使用。 事实上, 适合的表层结构学可以反映线性 MPC 的最佳控制法。 遵循这个方向, 我们在本文件中显示, 峰值 PWQ 函数可以通过最大值来精确描述, 只有一个隐藏层和两个神经元 。