论文标题
difftune $^+$：使用自动差异的无效自动调节
DiffTune$^+$: Hyperparameter-Free Auto-Tuning using Auto-Differentiation
论文作者
论文摘要
控制器调整是确保控制器提供其设计的性能的重要步骤。 Difftune已被提出为一种自动调整方法，该方法将动态系统和控制器展开到计算图中，并使用自动差异来获取控制器参数更新的梯度。但是，DiFftune使用香草梯度下降来迭代更新参数，在该参数中，性能在很大程度上取决于学习率的选择（作为超参数）。在本文中，我们建议使用不含高参数的方法来更新控制器参数。我们通过最大化减少损失来找到最佳参数更新，在该损失减少的情况下，基于近似状态和控制的预测损失用于最大化。提出了两种方法以最佳更新参数，并将其与杜宾汽车和四型四型的模拟中的相关变体进行比较。仿真实验表明，所提出的一阶方法的表现优于基于高参数的方法，并且比二阶无参数方法更健壮。
Controller tuning is a vital step to ensure the controller delivers its designed performance. DiffTune has been proposed as an automatic tuning method that unrolls the dynamical system and controller into a computational graph and uses auto-differentiation to obtain the gradient for the controller's parameter update. However, DiffTune uses the vanilla gradient descent to iteratively update the parameter, in which the performance largely depends on the choice of the learning rate (as a hyperparameter). In this paper, we propose to use hyperparameter-free methods to update the controller parameters. We find the optimal parameter update by maximizing the loss reduction, where a predicted loss based on the approximated state and control is used for the maximization. Two methods are proposed to optimally update the parameters and are compared with related variants in simulations on a Dubin's car and a quadrotor. Simulation experiments show that the proposed first-order method outperforms the hyperparameter-based methods and is more robust than the second-order hyperparameter-free methods.
