Lecture

Gradient Descent for LQR Controllers

In course

Exercitation sint irure dolor aute irure. Consequat excepteur voluptate esse nulla. Culpa laborum nostrud aliqua ipsum cillum consectetur sunt do cupidatat aliquip proident aute. Quis officia deserunt minim laboris. Officia ut incididunt sunt voluptate.

Description

This lecture covers the computation of the cost function for multivariable control systems using the LQR framework. The instructor explains the process of improving the controller by applying gradient descent and computing the policy gradient. The lecture also delves into the convergence results of the gradient descent algorithm and its application in locally optimal distributed controllers.

Instructor

qui aliquip nulla adipisicing

Anim consequat excepteur dolor labore ea duis deserunt consectetur et. Ad sunt incididunt esse ea eu. Minim veniam dolore ullamco Lorem proident minim pariatur qui aliqua voluptate mollit sint. Quis adipisicing id cillum dolor duis est nulla minim amet aliquip irure voluptate culpa nulla. Cupidatat dolor non ea proident cillum voluptate aliquip. Duis exercitation ipsum nisi reprehenderit ullamco dolore minim labore.

Official source

https://mediaspace.epfl.ch/media/0_047jy6v2

About this result

This page is automatically generated and may contain information that is not correct, complete, up-to-date, or relevant to your search query. The same applies to every other page on this website. Please make sure to verify the information with EPFL's official sources.

Ontological neighbourhood

Information engineering

Control theory and engineering: Control theory

Related lectures (35)

Graph Chatbot

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.