Showing physics.flu-dynShow all
2 papers · 1 filter
physics.flu-dyn2026
Gradient-free learning of a closed-loop wall controller for turbulent drag reduction
Giorgio Maria Cavallazzi, Miguel Pérez Cuadrado, Alfredo Pinelli
Closed-loop wall controllers learnt by multi-agent reinforcement learning are usually trained on periodic boxes far smaller than the flows they are meant to drive, and a large part…
physics.flu-dyn2026
Reward hacking in physical reinforcement learning revealed by turbulent drag reduction
Giorgio Maria Cavallazzi, Miguel Pérez-Cuadrado, Alfredo Pinelli
Reinforcement-learning controllers optimise specified rewards, but in physical systems those rewards often capture only part of the true control objective. Three mechanisms through…