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

Stabilizing an unknown control system is one of the most fundamental problemsin control systems engineering. In this paper, we provide a simple, model-freealgorithm for stabilizing fully observed dynamical systems. While model-freemethods have become increasingly popular in practice due to their simplicityand flexibility, stabilization via direct policy search has receivedsurprisingly little attention. Our algorithm proceeds by solving a series ofdiscounted LQR problems, where the discount factor is gradually increased. Weprove that this method efficiently recovers a stabilizing controller for linearsystems, and for smooth, nonlinear systems within a neighborhood of theirequilibria. Our approach overcomes a significant limitation of prior work,namely the need for a pre-given stabilizing control policy. We empiricallyevaluate the effectiveness of our approach on common control benchmarks.

Stabilizing Dynamical Systems via Policy Gradient Methods