Swimming fish. Prof. Petros Koumoutsakos, 2017.
Zur Person
Petros Koumoutsakos has received an education in Naval Architecture, Aeronautics and Applied Mathematics. He was appointed as Chair for Computational Science at ETH Zurich in 2000. Petros is elected Fellow of the American Society of Mechanical Engineers (ASME), the American Physical Society (APS) and the Society of Industrial and Applied Mathematics (SIAM). He is recipient the Advanced Investigator Award by the European Research Council and led the team that won the ACM Gordon Bell prize in Supercomputing (2013). His team researches the how and what of computing as applied to problems ranging from fish swimming to nanotechnology.
Abstract
We often learn a new game by observing others or by playing and losing/winning the game ourselves. This observation constitute the core of reinforcement learning an algorithm that has applications in areas ranging from psychology to fluid dynamics. In this talk I will demonstrate how reinforcement learning assists in performing synchronised swimming of multiple artificial swimmers. Lessons learned by interfacing natural laws and learning algorithms will be discussed.