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

Imitation learning enables the synthesis of controllers for complexobjectives and highly uncertain plant models. However, methods to providestability guarantees to imitation learned controllers often rely on largeamounts of data and/or known plant models. In this paper, we explore aninput-output (IO) stability approach to dissipative imitation learning, whichachieves stability with sparse data sets and with little known about the plantmodel. A closed-loop stable dynamic output feedback controller is learned usingexpert data, a coarse IO plant model, and a new constraint to enforcedissipativity on the learned controller. While the learning objective isnonconvex, iterative convex overbounding (ICO) and projected gradient descent(PGD) are explored as methods to successfully learn the controller. This newimitation learning method is applied to two unknown plants and compared totraditionally learned dynamic output feedback controller and neural networkcontroller. With little knowledge of the plant model and a small data set, thedissipativity constrained learned controller achieves closed loop stability andsuccessfully mimics the behavior of the expert controller, while other methodsoften fail to maintain stability and achieve good performance.

Dissipative Imitation Learning for Discrete Dynamic Output Feedback Control with Sparse Data Sets