Deep Reinforcement Learning for Fluid Dynamics and Control - presented by Prof. Steven L. Brunton

Deep Reinforcement Learning for Fluid Dynamics and Control

Prof. Steven L. Brunton

Prof. Steven L. Brunton
Ask the seminar a question! BETA
Deep Reinforcement Learning for Fluid Dynamics and Control
Prof. Steven L. Brunton
Steven L. Brunton
University of Washington

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.

References
  • 1.
    S. L. Brunton et al. (2019) Machine Learning for Fluid Mechanics. Annual Review of Fluid Mechanics
  • 2.
    S. Verma et al. (2018) Efficient collective swimming by harnessing vortices through deep reinforcement learning. Proceedings of the National Academy of Sciences
  • 3.
    G. Novati et al. (2021) Automating turbulence modelling by multi-agent reinforcement learning. Nature Machine Intelligence
  • 4.
    https://doi.org/10.48550/arXiv.1908.04127
  • 5.
    J. Rabault et al. (2019) Artificial neural networks trained through deep reinforcement learning discover control strategies for active flow control. Journal of Fluid Mechanics
  • 6.
    D. Fan et al. (2020) Reinforcement learning for bluff body active flow control in experiments and simulations. Proceedings of the National Academy of Sciences
  • 7.
    P. Ma et al. (2018) Fluid directed rigid body control using deep reinforcement learning. ACM Transactions on Graphics
  • 8.
    https://papers.nips.cc/paper/2003/file/b427426b8acd2c2e53827970f2c2f526-Paper.pdf
  • 9.
    https://proceedings.neurips.cc/paper/2006/file/98c39996bf1543e974747a2549b3107c-Paper.pdf
  • 10.
    P. Abbeel et al. (2010) Autonomous Helicopter Aerobatics through Apprenticeship Learning. The International Journal of Robotics Research
  • 11.
    https://groups.csail.mit.edu/robotics-center/public_papers/Tedrake09.pdf
  • 12.
    https://doi.org/10.48550/arXiv.1707.05110
  • 13.
    G. Reddy et al. (2016) Learning to soar in turbulent environments. Proceedings of the National Academy of Sciences
  • 14.
    J. Xu et al. (2019) Learning to fly. ACM Transactions on Graphics
Brunton Lab logo
Reinforcement learning
Brunton Lab (University of Washington)
Cite as
S. L. Brunton (2021, March 5), Deep Reinforcement Learning for Fluid Dynamics and Control
DOI
doi.org/10.52843/cassyni.kvtnvy
Export
Citations
Share
Timestamped permalink
Details
Listed seminar This seminar is open to all
Recorded Available to all
Video length 17:34