This paper presents a parameterization of nonlinear controllers for uncertain systems building on a recently developed neural network architecture, called the recurrent equilibrium network (REN), and a nonlinear version of the Youla parameterization. The proposed framework has "built-in" guarantees of stability, i.e., all policies in the search space result in a contracting (globally exponentially stable) closed-loop system. Thus, it requires very mild assumptions on the choice of cost function and the stability property can be generalized to unseen data. Another useful feature of this approach is that policies are parameterized directly without any constraints, which simplifies learning by a broad range of policy-learning methods based on unconstrained optimization (e.g. stochastic gradient descent). We illustrate the proposed approach with a variety of simulation examples.
翻译:本文件介绍了基于最近开发的神经网络结构(称为经常平衡网络(REN))和非线性版本的Youla参数化的非线性控制器对不确定系统的参数化。拟议的框架具有稳定性的“内在”保证,即搜索空间中的所有政策都导致一个(全球指数性稳定)闭环系统。因此,它要求对成本功能的选择和稳定性属性进行非常温和的假设,将其普遍化为不可见的数据。这一方法的另一个有用特征是,在没有任何限制的情况下直接对政策进行参数化,这通过以不受限制的优化为基础的广泛的政策学习方法(例如,随机梯度梯度梯度梯度梯度梯度梯度梯度梯度梯度梯度梯度梯度梯度)简化学习过程。我们用各种模拟例子来说明拟议的方法。