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

This article presents a constrained policy optimization approach for theoptimal control of systems under nonstationary uncertainties. We introduce anassumption that we call Markov embeddability that allows us to cast thestochastic optimal control problem as a policy optimization problem over theaugmented state space. Then, the infinite-dimensional policy optimizationproblem is approximated as a finite-dimensional nonlinear program by applyingfunction approximation, deterministic sampling, and temporal truncation. Theapproximated problem is solved by using automatic differentiation andcondensed-space interior-point methods. We formulate several conceptual andpractical open questions regarding the asymptotic exactness of theapproximation and the solution strategies for the approximated problem. As aproof of concept, we provide a numerical example demonstrating the performanceof the control policy obtained by the proposed method.

Constrained Policy Optimization for Stochastic Optimal Control under Nonstationary Uncertainties