BEGIN:VCALENDAR
VERSION:2.0
PRODID:OpenCms 21.0.11
BEGIN:VTIMEZONE
TZID:Europe/Berlin
X-LIC-LOCATION:Europe/Berlin
BEGIN:DAYLIGHT
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
DTSTART:19700329T020000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=3
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
DTSTART:19701025T030000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10
END:STANDARD
END:VTIMEZONE				
BEGIN:VEVENT
DTSTAMP:20230509T150212
UID:b6f7e7ae-ee69-11ed-985d-000e0c3db68b
SUMMARY:Talk of Prof. Sebastien Gros
DESCRIPTION:Prof. Sebastien Gros\nDepartment of Engineering Cybernetics\nNorwegian University of Science and Technology\nTrondheim, Norway  \nTuesday 2023-05-16 4:00 p.m.\nIST Seminar Room 2.255 - Pfaffenwaldring 9 - Campus Stuttgart-Vaihingen  \nAbstract\nMachine Learning and AI are quickly permeating all aspects of our society, and all technical\napplications. Control and optimization do not escape that trend. In “general” optimal control, the\nmost broadly visible AI tools are based on Reinforcement Learning (RL), with some very public\nsuccesses such as AlphaZero and ChatGPT today. Despite these successes, pure AI-based tools face\ncertain difficulties when approaching demanding applications where, e.g., safety or FEAT (fairness,\nexplainability, accountability, transparency) are necessary. In that context, the more classic\ntools central in control communities are highly relevant. In particular, MPC is a central tool for\nsafety and FEAT.\nIn this talk, we will introduce the necessary concepts to establish a synergy between MPC and\nRL. In particular, we will discuss how RL tools allow us to view MPC as "model of optimality”\nrather than a model-based policy. That view makes it possible to generate learning-based optimal\npolicies using MPC, even if the predictions (or model) underlying the MPC scheme are inaccurate.\nConversely, this view allows to introduce structure in RL. We will then discuss the role of the MPC\nmodel in that learning context. Relating MPC to RL requires establishing strong connections between\nMPC and Markov Decision Processes (MDPs). This talk will also briefly discuss some novel results\nderiving from that connections.  \nBiographical Information\nSebastien Gros has received his PhD degree from EPFL in 2008, focusing on data-driven\noptimization and control. After a bike trip from Switzerland to the Everest base camp, and a one\nyear experience in the wind industry, he has joined KU Leuven for a postdoc in numerical\noptimization and real-time MPC. He became assistant Prof. in 2013 at Chalmers University of Tech.,\nSweden, and associate Prof. in 2016. In 2019 he joined the Dept. Of Cybernetic, NTNU, Norway as a\nfull Prof. He has become head of that Dept. in 2022. His research interests include MPC, Optimal\nControl, Markov Decision Processes, Stochastic Optimal Control and Reinforcement Learning. His\napplications focus on energy-related problems. 
DTSTART;TZID=Europe/Berlin;VALUE=DATE:20230516
URL;VALUE=URI:https://www.ist.uni-stuttgart.de/events/Talk-of-Prof.-Sebastien-Gros/
END:VEVENT
END:VCALENDAR