.png){kind=icon}
.png){kind=icon}
Return
Stabilizing reinforcement learning control: A modular framework for optimizing over all stable behavior
.png){kind=icon}
OA
AI
DOI：10.1016/j.automatica.2024.111642.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
We propose a framework for the design of feedback controllers that combines the optimization -driven and model -free advantages of deep reinforcement learning with the stability guarantees provided by using the Youla-Ku & ccaron;era parameterization to define the search domain. Recent advances in behavioral systems allow us to construct a data -driven internal model; this enables an alternative realization of the Youla-Ku & ccaron;era parameterization based entirely on input-output exploration data. Perhaps of independent interest, we formulate and analyze the stability of such data -driven models in the presence of noise. The Youla-Ku & ccaron;era approach requires a stable parameterfor controller design. For the training of reinforcement learning agents, the set of all stable linear operators is given explicitly through a matrix factorization approach. Moreover, a nonlinear extension is given using a neural network to express a parameterized set of stable operators, which enables seamless integration with standard deep learning libraries. Finally, we show how these ideas can also be applied to tune fixed -structure controllers (c) 2024 The Author(s). Published by Elsevier Ltd. This is an open access article under the CC BY license (http://creativecommons.org/licenses/by/4.0/).
Keywords:
Reinforcement learning
Data -driven control
Youla-Ku & ccaron
era parameterization
Neural networks
Stability
Process control
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
5.9
Papers:
1.2W
Citations:
5.2W