English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

This paper studies the learning-to-control problem under process and sensinguncertainties for dynamical systems. In our previous work, we developed adata-based generalization of the iterative linear quadratic regulator (iLQR) todesign closed-loop feedback control for high-dimensional dynamical systems withpartial state observation. This method required perfect simulation rolloutswhich are not realistic in real applications. In this work, we brieflyintroduce this method and explore its efficacy under process and sensinguncertainties. We prove that in the fully observed case where the systemdynamics are corrupted with noise but the measurements are perfect, it stillconverges to the global minimum. However, in the partially observed case whereboth process and measurement noise exist in the system, this method convergesto a biased "optimum". Thus multiple rollouts need to be averaged to retrievethe true optimum. The analysis is verified in two nonlinear robotic examplessimulated in the above cases.

Learning to Control under Uncertainty with Data-Based Iterative Linear Quadratic Regulator