.png){kind=icon}
.png){kind=icon}
Return
Safe Approximate Dynamic Programming via Kernelized Lipschitz Estimation
.png){kind=icon}
OA
AI
DOI：10.1109/TNNLS.2020.2978805.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
We develop a method for obtaining safe initial policies for reinforcement learning via approximate dynamic programming (ADP) techniques for uncertain systems evolving with discrete-time dynamics. We employ the kernelized Lipschitz estimation to learn multiplier matrices that are used in semidefinite programming frameworks for computing admissible initial control policies with provably high probability. Such admissible controllers enable safe initialization and constraint enforcement while providing exponential stability of the equilibrium of the closed-loop system.
Keywords:
Estimation
Dynamic programming
Learning systems
Kernel
Safety
Data models
Programming
Approximate dynamic programming (ADP)
data-driven Lipschitz constant estimation
incremental quadratic constraints
kernel density estimation (KDE)
semidefinite programming
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
8.9
Papers:
7.5K
Citations:
7.2W
View more organizations