Offline-trained recurrent neural estimator for opposition control in turbulence fails in closed loop due to controller-induced distribution shift but is stabilized by closed-loop retraining and spectral consistency on actuation.
A review on deep reinforcement learning for fluid mechanics.Computers & Fluids, 225:104973, July 2021
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
years
2026 4roles
background 2polarities
background 2representative citing papers
Reward hacking in RL for wall-turbulence control is exposed through mass-conserving projection, memoryless policies, and pressure-gradient rewards; fixes yield honest 17% drag reduction.
Reformulating DRL in a moving reference frame enables reliable control of rapid transitions between mode-locked states in a 1D RDE model by separating fast detonation propagation from slower operating-mode dynamics.
A unified training framework for mesh-based ML surrogates in CFD improves accuracy and long-horizon stability by enforcing spatial derivative consistency via multi-node prediction, using temporal cross-attention correction, and adding 3D rotary positional embeddings.
citing papers explorer
-
Offline accuracy is not enough: closed-loop instability and stabilisation of a wall-sensor neural estimator in opposition control
Offline-trained recurrent neural estimator for opposition control in turbulence fails in closed loop due to controller-induced distribution shift but is stabilized by closed-loop retraining and spectral consistency on actuation.
-
Reward hacking in physical reinforcement learning revealed by turbulent drag reduction
Reward hacking in RL for wall-turbulence control is exposed through mass-conserving projection, memoryless policies, and pressure-gradient rewards; fixes yield honest 17% drag reduction.
-
Timescale Separation Enables Deep Reinforcement Learning Control of Rotating Detonation Engine Mode Transitions
Reformulating DRL in a moving reference frame enables reliable control of rapid transitions between mode-locked states in a 1D RDE model by separating fast detonation propagation from slower operating-mode dynamics.
-
Mesh Based Simulations with Spatial and Temporal awareness
A unified training framework for mesh-based ML surrogates in CFD improves accuracy and long-horizon stability by enforcing spatial derivative consistency via multi-node prediction, using temporal cross-attention correction, and adding 3D rotary positional embeddings.