Stability-certified reinforcement learning control via spectral normalization
In this study, two types of methods from different perspectives based on spectral normalization (SN) are described for ensuring the stability of a feedback system controlled by a neural network (NN). The first one is that the L2gain of the feedback system is bounded less than 1 to satisfy a stabilit...
Main Authors: | Ryoichi Takase, Nobuyuki Yoshikawa, Toshisada Mariyama, Takeshi Tsuchiya |
---|---|
Format: | Article |
Language: | English |
Published: |
Elsevier
2022-12-01
|
Series: | Machine Learning with Applications |
Subjects: | |
Online Access: | http://www.sciencedirect.com/science/article/pii/S2666827022000846 |
Similar Items
-
New stability criteria for systems with an interval time-varying delay
by: Junkang Tian, et al.
Published: (2023-01-01) -
Output Stabilization of Linear Systems in Given Set
by: Ba Huy Nguyen, et al.
Published: (2023-08-01) -
Stability margins for generalized fractional two-dimensional state space models
by: Souad Salmi, et al.
Published: (2024-03-01) -
Stability Analysis of Linear Systems under Time-Varying Samplings by a Non-Standard Discretization Method
by: Xiefu Jiang, et al.
Published: (2018-10-01) -
Quadratic Stabilization of Linear Uncertain Positive Discrete-Time Systems
by: Dušan Krokavec, et al.
Published: (2021-09-01)