BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:The shades of reinforcement learning
DTSTART:20200311T141500
DTEND:20200311T151500
DTSTAMP:20260924T095035Z
UID:7199c9c46ad0b36391a9cf9fa5ebc25faa2ab5b02cd9e73e91d6cd1b
CATEGORIES:Conferences - Seminars
DESCRIPTION:Prof. John Tsitsiklis\nAbstract:\nWe review the scope of reinf
 orcement learning and argue that it is about several different problems\, 
 each one bringing about different challenges: offline learning based on a 
 model\, a simulator\, historical data\, or experiments with a physical sys
 tem\, as well as online learning. We also review the main types of reinfor
 cement learnign algoirithms (value function approximation\, policy learnin
 g\, and actor-critic methods)\, and conclude with a discussion of research
  directions.\n\nShort-Bio:\nJohn N. Tsitsiklis was born in Thessaloniki\, 
 Greece\, in 1958. He received the B.S. degree in Mathematics (1980)\, and 
 the B.S. (1980)\, M.S. (1981)\, and Ph.D. (1984) degrees in Electrical Eng
 ineering\, all from the Massachusetts Institute of Technology\, Cambridge\
 , Massachusetts\, U.S.A.During the academic year 1983-84\, he was an actin
 g assistant professor of Electrical Engineering at Stanford University\, S
 tanford\, California. Since 1984\, he has been with the department of Elec
 trical Engineering and Computer Science (EECS) at the Massachusetts Instit
 ute of Technology (MIT)\, where he is currently a Clarence J Lebel Profess
 or of Electrical Engineering.\n\nmore info
LOCATION:BC 420 https://plan.epfl.ch/?room==BC%20420
STATUS:CANCELLED
END:VEVENT
END:VCALENDAR