A Caltech Library Service

Robust Model-Free Learning and Control without Prior Knowledge

Ho, Dimitar and Doyle, John C. (2019) Robust Model-Free Learning and Control without Prior Knowledge. In: 2019 IEEE 58th Conference on Decision and Control (CDC). IEEE , Piscataway, NJ, pp. 4577-4582. ISBN 978-1-7281-1398-2.

Full text is not posted in this repository. Consult Related URLs below.

Use this Persistent URL to link to this item:


We present a simple model-free control algorithm that is able to robustly learn and stabilize an unknown discretetime linear system with full control and state feedback subject to arbitrary bounded disturbance and noise sequences. The controller does not require any prior knowledge of the system dynamics, disturbances or noise, yet can guarantee robust stability, uniform asymptotic bounds and uniform worst-case bounds on the state-deviation. Rather than the algorithm itself, we would like to highlight the new approach taken towards robust stability analysis which served as a key enabler in providing the presented stability and performance guarantees. We will conclude with simulation results that show that despite the generality and simplicity, the controller demonstrates good closed-loop performance.

Item Type:Book Section
Related URLs:
URLURL TypeDescription
Doyle, John C.0000-0002-1828-2486
Additional Information:© 2019 IEEE.
Record Number:CaltechAUTHORS:20200911-071601902
Persistent URL:
Official Citation:D. Ho and J. C. Doyle, "Robust Model-Free Learning and Control without Prior Knowledge," 2019 IEEE 58th Conference on Decision and Control (CDC), Nice, France, 2019, pp. 4577-4582, doi: 10.1109/CDC40024.2019.9029986
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:105315
Deposited By: Tony Diaz
Deposited On:11 Sep 2020 16:18
Last Modified:16 Nov 2021 18:42

Repository Staff Only: item control page