A Caltech Library Service

Passive-Aggressive Learning and Control

Ho, Dimitar and Matni, Nikolai and Doyle, John C. (2018) Passive-Aggressive Learning and Control. In: 2018 Annual American Control Conference (ACC). IEEE , Piscataway, NJ, pp. 1887-1894. ISBN 978-1-5386-5428-6.

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

Use this Persistent URL to link to this item:


In this work, we investigate the problem of simultaneously learning and controlling a system subject to adversarial choices of disturbances and system parameters. We study the problem for a scalar system with l∞ -norm bounded disturbances and system parameters constrained to lie in a known bounded convex polytope. We present a controller that is globally stabilizing and gives continuously improving bounds on the worst case state deviation. The proposed controller simultaneously learns the system parameters and controls the system. The controller emerges naturally from an optimization problem, and balances exploration and exploitation in such a way that it is able to efficiently stabilize unstable and adversarial system dynamics. Specifically if the controller is faced with large uncertainty, the initial focus is on exploration, retrieving information about the system by applying state-feedback controllers with varying gains and signs. In a prespecified bounded region around the origin, our control strategy can be seen as passive in the sense that it learns very little information. Only once the noise and/or system parameters act in an adversarial way, leading to the the state exiting the aforementioned region for more than one time-step, our proposed controller behaves aggressively in that it is guaranteed to learn enough about the system to subsequently robustly stabilize it. We end by demonstrating the efficiency of our methods via numerical simulations.

Item Type:Book Section
Related URLs:
URLURL TypeDescription
Matni, Nikolai0000-0003-4936-3921
Doyle, John C.0000-0002-1828-2486
Additional Information:© 2018 AACC. Thanks to funding from AFOSR and NSF and gifts from Huawei and Google.
Funding AgencyGrant Number
Air Force Office of Scientific Research (AFOSR)UNSPECIFIED
Record Number:CaltechAUTHORS:20190205-082240504
Persistent URL:
Official Citation:D. Ho, N. Matni and J. C. Doyle, "Passive-Aggressive Learning and Control," 2018 Annual American Control Conference (ACC), Milwaukee, WI, 2018, pp. 1887-1894. doi: 10.23919/ACC.2018.8430904
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:92653
Deposited By: Tony Diaz
Deposited On:05 Feb 2019 19:13
Last Modified:03 Oct 2019 20:46

Repository Staff Only: item control page