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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

This paper presents a policy parameterization for learning-based control onnonlinear, partially-observed dynamical systems. The parameterization is basedon a nonlinear version of the Youla parameterization and the recently proposedRecurrent Equilibrium Network (REN) class of models. We prove that theresulting Youla-REN parameterization automatically satisfies stability(contraction) and user-tunable robustness (Lipschitz) conditions on theclosed-loop system. This means it can be used for safe learning-based controlwith no additional constraints or projections required to enforce stability orrobustness. We test the new policy class in simulation on two reinforcementlearning tasks: 1) magnetic suspension, and 2) inverting a rotary-arm pendulum.We find that the Youla-REN performs similarly to existing learning-based andoptimal control methods while also ensuring stability and exhibiting improvedrobustness to adversarial disturbances.

Learning Over Contracting and Lipschitz Closed-Loops for Partially-Observed Nonlinear Systems (Extended Version)