DiffTune+: Hyperparameter-Free Auto-Tuning using Auto-Differentiation
DiffTune+: Hyperparameter-Free Auto-Tuning using Auto-Differentiation
复制标题
DOI：
10.48550/arxiv.2212.03194
复制
发表时间：
2022-12
期刊：
影响因子：
--
通讯作者：
Sheng Cheng;Lin Song;Minkyung Kim;Shenlong Wang;N. Hovakimyan
中科院分区：
文献类型：
--
作者：
Sheng Cheng;Lin Song;Minkyung Kim;Shenlong Wang;N. Hovakimyan
控制器调优是确保控制器提供其设计性能的重要步骤。DiffTune已经被提出作为一种自动调整方法，该方法将动态系统和控制器展开为计算图，并使用自动微分来获得控制器参数更新的梯度。然而，DiffTune使用香草梯度下降来迭代更新参数，其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，我们提出使用超参数自由的方法来更新控制器参数。我们通过最大化损失减少来找到最优参数更新，其中基于近似状态和控制的预测损失用于最大化。提出了两种方法来优化更新的参数，并与相关的变种在模拟杜宾的车和四旋翼。仿真实验表明，所提出的一阶方法优于基于超参数的方法，比二阶超参数无方法更强大。
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.