Saved in:
Bibliographic Details
Main Authors: Sznaier, Mario, Bozdag, Mustafa
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2505.11641
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918023508525056
author Sznaier, Mario
Bozdag, Mustafa
author_facet Sznaier, Mario
Bozdag, Mustafa
contents Model agnostic controller learning, for instance by direct policy optimization, has been the object of renewed attention lately, since it avoids a computationally expensive system identification step. Indeed, direct policy search has been empirically shown to lead to optimal controllers in a number of cases of practical importance. However, to date, these empirical results have not been backed up with a comprehensive theoretical analysis for general problems. In this paper we use a simple example to show that direct policy optimization is not directly generalizable to other seemingly simple problems. In such cases, direct optimization of a performance index can lead to unstable pole/zero cancellations, resulting in the loss of internal stability and unbounded outputs in response to arbitrarily small perturbations. We conclude the paper by analyzing several alternatives to avoid this phenomenon, suggesting some new directions in direct control policy optimization.
format Preprint
id arxiv_https___arxiv_org_abs_2505_11641
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Challenges in Model Agnostic Controller Learning for Unstable Systems
Sznaier, Mario
Bozdag, Mustafa
Optimization and Control
Model agnostic controller learning, for instance by direct policy optimization, has been the object of renewed attention lately, since it avoids a computationally expensive system identification step. Indeed, direct policy search has been empirically shown to lead to optimal controllers in a number of cases of practical importance. However, to date, these empirical results have not been backed up with a comprehensive theoretical analysis for general problems. In this paper we use a simple example to show that direct policy optimization is not directly generalizable to other seemingly simple problems. In such cases, direct optimization of a performance index can lead to unstable pole/zero cancellations, resulting in the loss of internal stability and unbounded outputs in response to arbitrarily small perturbations. We conclude the paper by analyzing several alternatives to avoid this phenomenon, suggesting some new directions in direct control policy optimization.
title Challenges in Model Agnostic Controller Learning for Unstable Systems
topic Optimization and Control
url https://arxiv.org/abs/2505.11641