Skip to content

On the Convergence of the Iterative Linear Exponential Quadratic Gaussian Algorithm to Stationary Points

Authors
Vincent Roulet, Maryam Fazel, Siddhartha Srinivasa, Zaid Harchaoui
Year
2019
Preprint
Identifiers
arXiv 1910.08221

Abstract

A classical method for risk-sensitive nonlinear control is the iterative linear exponential quadratic Gaussian algorithm. We present its convergence analysis from a first-order optimization viewpoint. We identify the objective that the algorithm actually minimizes and we show how the addition of a proximal term guarantees convergence to a stationary point.

Knowledge Base

Map Tree Search

External

Document arXiv Abstract arXiv PDF arXiv HTML Google Scholar OpenAlex

Similar Papers