.png){kind=icon}
Return
World model-driven process industry operations: An offline reinforcement learning solution based on conditional diffusion
.png){kind=icon}
OA
AI
DOI：10.1016/j.compind.2026.104442.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• A diffusion-based world model is proposed to guide offline decision agent training. • A spatiotemporal Transformer is used for noise prediction in the diffusion model. • Reinforcement learning with behavior cloning is designed for continuous control. • The proposed framework is validated on a real tobacco shredding production line. • The validation shows a 17.2% quality improvement for process production control.
Keywords:
World model
Conditional diffusion
Offline reinforcement learning
Process industry operation
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
9.1
Papers:
2.9K
Citations:
1.1W
Organization
View more organizations
Cited Papers
.png){kind=icon}
ShareSaveA review On reinforcement learning: Introduction and applications in industrial process control
PREAI
ShareSave
ShareSave View more