Saved in:
Bibliographic Details
Main Authors: Xu, Nikki, Tran, Hien
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2510.25063
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911310661287936
author Xu, Nikki
Tran, Hien
author_facet Xu, Nikki
Tran, Hien
contents Controllers designed with reinforcement learning can be sensitive to model mismatch. We demonstrate that designing such controllers in a virtual simulation environment with an inaccurate model is not suitable for deployment in a physical setup. Controllers designed using an accurate model is robust against disturbance and small mismatch between the physical setup and the mathematical model derived from first principles; while a poor model results in a controller that performs well in simulation but fails in physical experiments. Sensitivity analysis is used to justify these discrepancies and an empirical region of attraction estimation help us visualize their robustness.
format Preprint
id arxiv_https___arxiv_org_abs_2510_25063
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Control Synthesis with Reinforcement Learning: A Modeling Perspective
Xu, Nikki
Tran, Hien
Systems and Control
Controllers designed with reinforcement learning can be sensitive to model mismatch. We demonstrate that designing such controllers in a virtual simulation environment with an inaccurate model is not suitable for deployment in a physical setup. Controllers designed using an accurate model is robust against disturbance and small mismatch between the physical setup and the mathematical model derived from first principles; while a poor model results in a controller that performs well in simulation but fails in physical experiments. Sensitivity analysis is used to justify these discrepancies and an empirical region of attraction estimation help us visualize their robustness.
title Control Synthesis with Reinforcement Learning: A Modeling Perspective
topic Systems and Control
url https://arxiv.org/abs/2510.25063