Online Performance Optimization of Nonlinear Systems: A Gray-Box Approach


Loading...

Date

2024-07

Publication Type

Conference Paper

ETH Bibliography

yes

Citations

Altmetric

Data

Abstract

We propose a gray-box controller to optimize the performance of a nonlinear system in an online manner. This is motivated by the observation that model-based and model-free approaches own complementary benefits in sample efficiency and optimality in the presence of inaccurate models. To achieve the best of both worlds, our controller incorporates approximate model information into model-free updates via adaptive convex combinations. Further, it leverages real-time outputs of the system and iteratively adjusts control inputs. We quantify conditions on the quality of approximate models that render the gray-box approach preferable to model-based or model-free approaches. We characterize the performance of our controller via dynamic regret in a constrained, time-varying setting, and highlight how the regret scales with the number of iterations, the problem dimension, and the cumulative effect of inaccurate models.

Publication status

published

Editor

Book title

ICML 2024 Workshop: Foundations of Reinforcement Learning and Control - Connections and Perspectives

Journal / series

Volume

Pages / Article No.

Publisher

OpenReview

Event

Workshop on Foundations of Reinforcement Learning and Control: Connections and Perspectives (FoRLac 2024)

Edition / version

Methods

Software

Geographic location

Date collected

Date created

Subject

Organisational unit

09478 - Dörfler, Florian / Dörfler, Florian
02650 - Institut für Automatik / Automatic Control Laboratory

Notes

Held in conjunction with the 41st International Conference on Machine Learning (ICML 2024) ; Poster presentation on July 26, 2024

Funding

Related publications and datasets