Deep Reinforcement Learning for Fluid Dynamics and Control

Reinforcement learning based on deep learning is currently being used for impressive control of fluid dynamic systems. This video will describe recent advances, including for mimicking the behavior of birds and fish, for turbulence closure modeling with sub-grid-scale models, and for robotic flight demonstrations. @eigensteve on Twitter Links to papers in video: @3:58 Machine learning for fluid mechanics Brunton, Noack, Koumoutsakos, Ann. Rev. Fluid Mech 52:477--508, 2020 @5:04 Efficient collective swimming by harnessing vortices through deep reinforcement learning Verma, Novati, Koumoutsakos, Proc. Nat. Acad. Sci. 115(23):5849--5854, 2018 @6:57 Automating turbulence modelling by multi-agent reinforcement learning Novati, Lascombes de Laroussilhe, Koumoutsakos, Nat. Mach. Int. 3:87--96, 2021 @8:47 A review