Active Flow Control Using Deep Reinforcement Learning with Time-Delays in Markov Decision Process and Autoregressive Policy

Engineering

• Reinforcement Learning 100%
• Markov Decision Process 50%
• Two Dimensional 33%
• Delay Time 33%
• Fluctuations 33%
• Reynolds' Number 33%
• Circular Cylinder 33%
• Cylinder 33%
• Hybrid 16%
• Models 16%
• Environment 16%
• Actuation 16%
• Control Actuation 16%
• Drag Reduction 16%
• Demonstrates 16%
• Freestream 16%
• Synthetic Jet Actuator 16%
• Reduced Order Model 16%
• Lift Force 16%
• Drag Force 16%

Physics

• Flow Control 66%
• Vortex Shedding 66%
• Policy 33%
• Drag 33%
• Standard 33%
• Coherent Control 33%
• Turbulence 33%
• Reynolds Number 33%
• Magnitude 16%
• Responses 16%
• Model 16%
• Environment 16%
• Frequencies 16%
• Physics 16%
• Eddy 16%
• Region 16%
• Wakes 16%
• Differences 16%
• Drag Reduction 16%
• Sampling 16%