BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Reinforcement Learning with Guarantees
DTSTART:20230120T110000
DTEND:20230120T120000
DTSTAMP:20260407T095522Z
UID:ef40c2eeb5ef8f6ca3a4530c607ca5bb684382808c44206686bffc07
CATEGORIES:Conferences - Seminars
DESCRIPTION:Prof Mario Zanon\nABSTRACT\nRL is a very successful approach t
 o optimal control\, which\, however\, struggles to provide explainability 
 and strong guarantees on the behavior of the resulting control scheme. In 
 contrast\, MPC is a standard tool for the closed-loop optimal control of c
 omplex systems with constraints and limitations and benefits from a rich t
 heory to assess closed-loop behavior. Because of model inaccuracy\, howeve
 r\, MPC can fail at delivering satisfactory closed-loop performance. This 
 seminar will discuss how to leverage the advantages of the two technique
 s\, offering a path toward safe and explainable RL.\n \nBIO\nI received m
 y B.Sc. in Industrial Engineering from the University of Trento in 2008 an
 d my M.Sc. in 2010 in Mechatronics and in General Engineering from the Uni
 versity of Trento and the Ecole Centrale Paris respectively in the context
  of a dual degree agreement. I obtained my Ph.D. in Electrical Engineering
  from the KU Leuven in 2015 under the supervision of Prof. Moritz Diehl. F
 rom November 2015 until December 2017\, I have been a postdoc researcher a
 t Chalmers University of Technology under the supervision of Prof. Paolo F
 alcone. From January 2018 until November 2021 I have been assistant profes
 sor at the IMT School for Advanced Studies Lucca\, where I became Associat
 e Professor in December 2021.\n\nMy research interests include Reinforceme
 nt Learning\, distributed MPC\, economic MPC\, optimal control and estimat
 ion of nonlinear dynamic systems\, in particular for aerospace and automot
 ive applications.
LOCATION:ME C2 405 https://plan.epfl.ch/?room==ME%20C2%20405
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR