Iterative Linearized Control: Stable Algorithms and Complexity Guarantees

arXiv1908.07615MaRDI QIDQ6323970FDOQ6323970

Authors: Vincent Roulet, S. S. Srinivasa, D. Drusvyatskiy, Zaid Harchaoui 

Publication date: 20 August 2019

Abstract: 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.

This page was built for publication: Iterative Linearized Control: Stable Algorithms and Complexity Guarantees

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6323970)