BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//132.216.98.100//NONSGML kigkonsult.se iCalcreator 2.20.4//
BEGIN:VEVENT
UID:20250724T193059EDT-6279US6VtN@132.216.98.100
DTSTAMP:20250724T233059Z
DESCRIPTION:Virtual Informal Systems Seminar (VISS) Centre for Intelligent 
 Machines (CIM) and Groupe d'Etudes et de Recherche en Analyse des Decision
 s (GERAD)\n	\n	Zoom Link\n	Meeting ID: 910 7928 6959 \n	Passcode: VISS\n	\n	Spea
 ker: Naci Saldi\, Assistant Professor\, Department of Natural and Mathemat
 ical Sciences\, Özyeğin University\, Turkey.\n	\n	Abstract:\n	\n	Decentralized
  stochastic control theory studies decisions of agents that are acting col
 lectively based on their local information to optimize a common cost funct
 ion under stochastic uncertainty. It will be a prominent avenue of researc
 h for many years to come as modern control systems are increasingly decent
 ralized and interconnected. In this talk\, we establish the existence of o
 ptimal policies for decentralized stochastic optimal control problems. We 
 first consider the static case and show the existence of optimal policies 
 under certain regularity conditions on the observation channels by introdu
 cing a topology on the set of policies. Then we consider sequential dynami
 c teams and establish the existence of an optimal policy via the static re
 duction method of Witsenhausen. We apply our findings to the well-known co
 unterexample of Witsenhausen.\n	\n	Biography:\n	\n	Naci Saldi received the B.S
 c. and M.S. degrees in Electrical and Electronics Engineering from Bilkent
  University in 2008 and 2010\, respectively and the Ph.D. degree in Depart
 ment of Mathematics and Statistics from Queen's University in 2015. He was
  a postdoctoral researcher at the University of Illinois at Urbana-Champai
 gn before joining the Department of Natural and Mathematical Sciences at Ö
 zyeğin University as an Assistant Professor. He is a co-author of the book
  Finite Approximations in Discrete-Time Stochastic Control\, published by 
 Springer. His research interests include stochastic and decentralized cont
 rol\, source coding\, mean-field games\, reinforcement learning\, and appl
 ied probability.\n
DTSTART:20211015T140000Z
DTEND:20211015T150000Z
LOCATION:CA\, ZOOM
SUMMARY:A Topology for Policies in Stochastic Teams and Existence of Optima
 l Policies
URL:/cim/channels/event/topology-policies-stochastic-t
 eams-and-existence-optimal-policies-334218
END:VEVENT
END:VCALENDAR