Skip to yearly menu bar Skip to main content


Iterative Linearized Control: Stable Algorithms and Complexity Guarantees

Vincent Roulet · Dmitriy Drusvyatskiy · Siddhartha Srinivasa · Zaid Harchaoui

Pacific Ballroom #39

Keywords: [ Robotics ] [ Planning and Control ] [ Optimization - Others ] [ Non-convex Optimization ]


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.

Live content is unavailable. Log in and register to view live content