BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Reinforcement Learning and Model Predictive Control\, where are we
 ?
DTSTART:20230919T140000
DTEND:20230919T150000
DTSTAMP:20260406T230106Z
UID:ab73fa64a9d087eb5294c70c44a4eefafbba1c543e897f0372a4acd4
CATEGORIES:Conferences - Seminars
DESCRIPTION:Sébastien Gros (NTNU\, Trondheim\, Norway)\nAbstract:\n\nThe
  use of data-driven methods in MPC has been drawing an important interest 
 in research over the past few years. Different techniques are being advoca
 ted\, often arguing for using tools from Machine Learning in the MPC model
 \, or even for using completely model-free approaches. The hope\, arguably
 \, is that improving the MPC predictions results in increased closed-loop 
 performance. However\, recent results show that when that performance is a
 ssessed in economic terms (energy\, emission\, production\, time\, money)\
 , the role of the MPC model is less obvious than usually assumed. In this 
 talk\, we will unpack this question. We will see how an MPC scheme is in f
 act a model of the solution of a Markov Decision Process as a whole\, rath
 er than a control tool built around a prediction model. This observation w
 ill allow us to connect MPC to Reinforcement Learning (RL)\, and understan
 d how to use RL techniques to improve the MPC closed-loop performance dire
 ctly. Finally\, this observation will also provide insights as to when MPC
  built with classic data-driven modelling techniques can be expected to pr
 oduce good closed-loop performance.\n\n \n\nBio:\n\nSebastien Gros receiv
 ed his Ph.D degree from EPFL\, Switzerland\, in 2007. After a journey by b
 icycle from Switzerland to the Everest base camp in full autonomy\, he joi
 ned a R&D group hosted at Strathclyde University focusing on wind turbine 
 control. In 2011\, he joined the university of KU Leuven as a postdoc\, wh
 ere his main research focus was on optimal control and fast MPC for comple
 x mechanical systems. He joined the Department of Signals and Systems at C
 halmers University of Technology\, Göteborg in 2013\, where he became ass
 ociate Prof. in 2017. He is now full Prof. and Head of Dept. of Cybernetic
 s at NTNU\, Norway and guest Prof. at Chalmers. His main research interest
 s include MPC\, Markov Decision Processes\, Learning for MPC\, Economic MP
 C\, stochastic optimal control\, Reinforcement Learning\, numerical method
 s\, and energy-related applications.
LOCATION:ME C2 405 https://plan.epfl.ch/?room==ME%20C2%20405
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR