To Learn or Not to Learn: A Litmus Test for Using Reinforcement Learning in Control

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Schulte, Victor, Eichelbeck, Michael, Althoff, Matthias
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917403217100800
author Schulte, Victor
Eichelbeck, Michael
Althoff, Matthias
author_facet Schulte, Victor
Eichelbeck, Michael
Althoff, Matthias
contents Reinforcement learning (RL) can be a powerful alternative to classical control methods when standard model-based control is insufficient, e.g., when deriving a suitable model is intractable or impossible. In many cases, however, the choice between model-based and RL-based control is not obvious. Due to the high computational costs of training RL agents, RL-based control should be limited to cases where it is expected to yield superior results compared to model-based control. To the best of our knowledge, there exists no approach to quantify the benefit of RL-based control that does not require RL training. In this work, we present a computationally efficient, purely simulation-based litmus test predicting whether RL-based control is superior to model-based control. Our test evaluates the suitability of the given model for model-based control by analyzing the impact of model uncertainties on the control problem. For this, we use reachset-conformant model identification combined with simulation-based analysis. This is followed by a learnability evaluation of the uncertainties based on correlation analysis. This two-part analysis enables an informed decision on the suitability of RL for a control problem without training an RL agent. We apply our test to several benchmarks, demonstrating its applicability to a wide range of control problems and highlight the potential to save computational resources.
format Preprint
id arxiv_https___arxiv_org_abs_2604_11463
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle To Learn or Not to Learn: A Litmus Test for Using Reinforcement Learning in Control
Schulte, Victor
Eichelbeck, Michael
Althoff, Matthias
Systems and Control
Reinforcement learning (RL) can be a powerful alternative to classical control methods when standard model-based control is insufficient, e.g., when deriving a suitable model is intractable or impossible. In many cases, however, the choice between model-based and RL-based control is not obvious. Due to the high computational costs of training RL agents, RL-based control should be limited to cases where it is expected to yield superior results compared to model-based control. To the best of our knowledge, there exists no approach to quantify the benefit of RL-based control that does not require RL training. In this work, we present a computationally efficient, purely simulation-based litmus test predicting whether RL-based control is superior to model-based control. Our test evaluates the suitability of the given model for model-based control by analyzing the impact of model uncertainties on the control problem. For this, we use reachset-conformant model identification combined with simulation-based analysis. This is followed by a learnability evaluation of the uncertainties based on correlation analysis. This two-part analysis enables an informed decision on the suitability of RL for a control problem without training an RL agent. We apply our test to several benchmarks, demonstrating its applicability to a wide range of control problems and highlight the potential to save computational resources.
title To Learn or Not to Learn: A Litmus Test for Using Reinforcement Learning in Control
topic Systems and Control
url https://arxiv.org/abs/2604.11463