Control of complex dynamics using reinforcement learning

Abstract

In this talk, we will focus on flow control -- a subject that has attracted numerous research efforts in the last decades -- and more specifically Reinforcement Learning (RL) as an alternative framework to standard techniques of control. RL encompasses a large variety of algorithms and strategies and has gained traction in recent years, due to the possibility of tackling the control of nonlinear systems while circumventing preliminary modelling steps. Indeed, RL algorithms do not require any a-priori knowledge of the equations governing the system to be controlled and solely rely on the local measurements of the flow, based on which a policy is learnt from the interaction of the agent with the environment. Despite successes, the first documented applications of RL for control in fluid dynamics often result in highly non-intuitive control policies, also when cheaper optimal solutions are available. We will discuss some examples of fluid mechanics interest, highlighting challenges as well as possible remedies for the current practice.

================================

Biography

Onofrio Semeraro received his PhD in Mechanical Engineering at KTH-Stockholm (Sweden) in 2013. He served as postdoctoral researcher at Ecole-Polytechnique, Palaiseau (France) and Politecnico of Bari (Italy), and he is currently a CNRS Research Associate since 2017, at the Laboratoire Interdisciplinaire des Sciences du Numérique (LISN) - Universite Paris Saclay, Orsay (France). His studies focus mainly on control, data assimilation, modelling and data-driven techniques, ranging from system identification to deep learning for fluid mechanics.