.png){kind=icon}
.png){kind=icon}
Return
Robust control by applying reinforcement learning to adapt explicit model predictive control policies
.png){kind=icon}
PRE
AI
E
T
S
DOI：10.1016/j.compchemeng.2025.109519.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• Reinforcement learning can address plant-model mismatch in optimal control. • Actor network initialised using explicit model predictive control policy. • Effects of evolving quadruple tank dynamics remedied in minimum phase region. • Agent failed with multivariable zero placement in a region about the origin. • Warm starting the critic improved reward yield in non-minimum phase region.
Keywords:
Safe Reinforcement Learning
Model Predictive Control
Actor-Critic
Nonlinear Process Control
Plant-model mismatch
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