Jun 2026
Offline Reinforcement Learning for Fluid Controls: Data-based Multi-observational Policy Extraction
This work develops a sensor position-conditioned architecture that enables a single policy network to adapt seamlessly to multiple sensor arrangements and demonstrates that the policy extraction from the dataset provides unprecedented flexibility for sensor placement optimization.
Deepak Akhare, Luning Sun, Xin-Yang Liu et al.
· arXiv.org · 0 citations