Title: 3 Easy Pieces: Learning to Model and Control Complex Systems
Abstract: I will present three learning algorithms fusing scientific computing and AI for the prediction and control of complex physical systems. The algorithms are:
(i) a multiscale approach to Learning the Effective Dynamics (LED) of complex systems
(ii) the Remember and Forget Experience Replay (ReFer) algorithm for reinforcement learning,and
(iii) a fusion of scientific computing and multi-agent reinforcement learning (SciMARL) for developing closures for unresolved dynamics of complex systems. I will describe the application of these algorithms to systems ranging from models in the AI gym to simulations of molecular systems and fish schooling.
I will argue that while RL is a potent modality for discovery of (causal?) flow mechanisms progress hinges on the proper incorporation of fluid mechanics knowledge in its algorithmic components.
Bio: Petros Koumoutsakos is Herbert S. Winokur, Jr. Professor of Engineering and Applied Sciences, Faculty Director of the Institute for Applied Computational Science (IACS) and Department Chair of Applied Mathematics at Harvard John A. Paulson School of Engineering and Applied Sciences (SEAS). He studied Naval Architecture (Diploma-NTU of Athens, M.Eng.-U. of Michigan), Aeronautics and Applied Mathematics (PhD-Caltech) and has served as the Chair of Computational Science at ETH Zurich (1997-2020). Petros is elected Fellow of the American Society of Mechanical Engineers (ASME), the American Physical Society (APS), the Society of Industrial and Applied Mathematics (SIAM). He is recipient of the Advanced Investigator Award by the European Research Council and the ACM Gordon Bell prize in Supercomputing. He is elected International Member to the US National Academy of Engineering (NAE). His research interests are on the fundamentals and applications of computing and artificial intelligence to understand, predict and optimize fluid flows in engineering, nanotechnology, and medicine.