BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//132.216.98.100//NONSGML kigkonsult.se iCalcreator 2.20.4//
BEGIN:VEVENT
UID:20260511T161004EDT-8064HdfAiL@132.216.98.100
DTSTAMP:20260511T201004Z
DESCRIPTION:\n	Virtual Informal Systems Seminar (VISS)\n\n	Centre for Intelli
 gent Machines (CIM) and Groupe d'Etudes et de Recherche en Analyse des Dec
 isions (GERAD)\n\n	Speaker: Rahul Jain – University of Southern California\
 , United States \n\n\n\n	Webinar link:\n		Webinar ID: 910 7928 6959\n		Passcode
 : VISS\n\n	Abstract:\n\n	Use of data-driven and learning methods for offline
  control design and real-time online control has become imperative for mod
 ern control systems that are increasingly complex\, expected to operate in
  uncertain\, non-stationary environments with a high degree of autonomy wh
 ile meeting various operational and safety requirements. In this talk\, I 
 will give a personal perspective of the challenges and recent advances mad
 e on learning and control problems. I will first talk about some of my con
 tributions to offline reinforcement learning for continuous (state and act
 ion space) control problems when a generative model is available. We will 
 see an application in robotics. I will then talk about recent developments
  and my contributions to online reinforcement learning for control in vari
 ous contexts: infinite and random horizon\, partial observability and mult
 i-agent settings. The focus will be on “regret” as a key measure of learni
 ng efficiency. Finally\, I will talk very briefly about control design whe
 n stringent safety specifications expressed in temporal logic languages mu
 st be satisfied\, both when the model is known and when it is unknown. Fin
 ally\, I will conclude with a discussion of new horizons especially when d
 riven by intelligent autonomy applications in robotics and other autonomou
 s systems.\n\n	Biography:\n\n	Rahul Jain is Professor of Electrical and Comp
 uter Engineering\, Computer Science* and ISE* (*by courtesy) at the Univer
 sity of Southern California (USC). He received a B.Tech from the IIT Kanpu
 r\, and an MA in Statistics and a PhD in EECS from the University of Calif
 ornia\, Berkeley. Prior to joining USC\, he was in the Mathematical Scienc
 es division at the IBM T J Watson Research Center\, Yorktown Heights\, NY.
  He is currently a Founding Director of the industry-sponsored USC Center 
 for AI and Autonomy. He has received numerous awards including the NSF CAR
 EER award\, the ONR Young Investigator award\, an IBM Faculty award\, the 
 James H. Zumberge Faculty Research and Innovation Award\, and has been a U
 S Fulbright Scholar. His interests span stochastic control\, reinforcement
  and statistical learning\, stochastic networks\, and game theory\, and en
 ergy systems and autonomous robotics on the applications side. The talk is
  based on joint work with a number of outstanding students and postdocs wh
 o are now themselves well-regarded academics.\n\n
DTSTART:20220325T180000Z
DTEND:20220325T190000Z
LOCATION:CA\, ZOOM
SUMMARY:Data-driven and learning-based methods for control: Challenges and 
 new horizons 
URL:https://www.mcgill.ca/cim/channels/event/data-driven-and-learning-based
 -methods-control-challenges-and-new-horizons-336545
END:VEVENT
END:VCALENDAR