BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//132.216.98.100//NONSGML kigkonsult.se iCalcreator 2.20.4//
BEGIN:VEVENT
UID:20260915T052129EDT-4849WLuVpE@132.216.98.100
DTSTAMP:20260915T092129Z
DESCRIPTION:GERAD Seminar\n\nSpeaker: Bora Yongacoglu – Queen's University
 \n\n \n\n\n	Event link\n\n	 \n\n	\n		Abstract\n		Game theoretic models are a popu
 lar framework for analyzing strategic interaction in systems with several 
 autonomous agents. In this talk\, we consider stochastic games and N-playe
 r mean-field games\, two models that are useful for studying multi-agent l
 earning. In this context\, we discuss common learning paradigms used for s
 electing policies and give special attention to simple algorithms that can
  be used under decentralized information. We will present structural resul
 ts on policy dynamics and illustrate how such results can guide algorithm 
 design. Finally\, we present a decentralized learning algorithm and analyz
 e its convergence to near equilibrium policies in several classes of games
 . \n\n	 \n\n	Bio:\n\n	Bio: Bora Yongacoglu is a post-doctoral fellow in the d
 epartment of mathematics and statistics at Queen's University. He recently
  received his PhD in mathematics at Queen's University\, where he was supe
 rvised by Serdar Yuksel and Gurdal Arslan. Before Queen's\, he studied eco
 nomics and mathematics at McGill University. His research focuses on multi
 -agent reinforcement learning and strategic dynamics in games. \n\n	\n		\n			\n				 
 \n			\n		\n	\n\n
DTSTART:20230215T160000Z
DTEND:20230215T170000Z
LOCATION:CA\, ZOOM
SUMMARY:Policy Revision Dynamics and Algorithm Design in Stochastic and Mea
 n-Field Games
URL:https://www.mcgill.ca/cim/channels/event/policy-revision-dynamics-and-a
 lgorithm-design-stochastic-and-mean-field-games-351774
END:VEVENT
END:VCALENDAR