.png){kind=icon}
.png){kind=icon}
Return
Safe reinforcement learning via adaptive robust model predictive shielding
.png){kind=icon}
OA
AI
H
S
DOI：10.1016/j.compchemeng.2025.109521.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• Propose Adaptive Robust Model Predictive Shielding for safe RL in process control. • Use offline-trained approximate robust NMPC backup for real-time safe deployment. • Embed adaptive safety parameter to reduce conservatism and improve performance.
Keywords:
Safe reinforcement learning
Model predictive shielding
Approximate model predictive control
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
C
IF:
3.9
Papers:
8.1K
Citations:
1.7W
Organization
No organization information available
Cited Papers