Iterative Linearized Control: Stable Algorithms and Complexity Guarantees
Iterative Linearized Control: Stable Algorithms and Complexity Guarantees
复制标题
DOI：
--
复制
发表时间：
2019-05
期刊：
影响因子：
--
通讯作者：
Vincent Roulet;D. Drusvyatskiy;S. Srinivasa;Zaïd Harchaoui
中科院分区：
文献类型：
--
作者：
Vincent Roulet;D. Drusvyatskiy;S. Srinivasa;Zaïd Harchaoui
We examine popular gradient-based algorithms for nonlinear control in the light of the modern complexity analysis of first-order optimization algorithms. The examination reveals that the complexity bounds can be clearly stated in terms of calls to a computational oracle related to dynamic programming and implementable by gradient back-propagation using machine learning software libraries such as PyTorch or TensorFlow. Finally, we propose a regularized Gauss-Newton algorithm enjoying worst-case complexity bounds and improved convergence behavior in practice. The software library based on PyTorch is publicly available.
