Thu, 19.01.2023 11:00

Learning polynomial optimal feedback laws of finite-horizon control problems

Group Seminar: Optimization and Optimal Control Group

Donato Vasquez Varas, RICAM

The problem of computing an optimal feedback law for a high dimensional, nonlinear, continuous time control system over a finite time horizon is considered. The approach consists in approximating the problem as a learning task in the space of multivariate polynomials. Results on the convergence and the generalization power of the solutions of the learning problem are provided. Finally, the capability of our approach to mitigate the curse of dimensionality is illustrated through high dimensional examples.

Thu, 19.01.2023 11:00 | RICAM, SP2 416-2

Back

This site uses cookies. They ensure essential functionalities of the website and enable us to continuously optimize content. Help us by agreeing to the collection of statistical data and the presentation of external multimedia content. You can change your cookie settings at any time. Further information can be found in the privacy settings and by clicking the Data Protection Link.

Necessary

These cookies are required for the smooth functioning of our website.

Name	Purpose	Storage duration	Type	Provider
CookieConsent	Remembers your consent to the use of cookies.	1 year	HTML	Web Consent
fe_typo_user	Assigns your browser to a session on the server. This only affects the content you see and is not evaluated or processed by us	-	HTTP	Web User

Statistics

With the help of these cookies, we strive to make our offer even more attractive for you. The user flow can be analyzed and assessed using pseudonymised data from website users. This gives us the opportunity to optimize website content.

Name	Purpose	Storage duration	Type	Provider
_pk_id	Used to store a few details about the user like unique visitor ID.	13 months	HTML	Matomo-id
_pk_ref	Used to store information about the user's referring website.	6 months	HTML	Matomo-ref
_pk_ses	Short-term cookie to save temporary data from the visit.	30 minutes	HTML	Matomo-ses
_pk_cvar	Short-term cookie to save temporary data from the visit.	30 minutes	HTML	Matomo-cvar
_pk_hsr	Short lived cookie used to temporarily store data for the visit.	30 minutes	HTML	Matomo

Multimedia

With the help of these cookies, we strive to improve the information we offer users by providing multimedia or interactive content such as videos.

Name	Purpose	Storage duration	Type	Provider
YouTube	A connection to YouTube will be established to view videos.	-	Connection	YouTube
SoundCloud	A connection to SoundCloud will be established to play audio files.	-	Connection	SoundCloud
Twitter	A connection to Twitter will be established to display tweets.	-	missing translation: type.	Twitter