BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:No-regret Dynamics for Multi-agent Learning - Alexander Terenin (U
 niversity of Cambridge)
DTSTART:20230412T100000Z
DTEND:20230412T113000Z
UID:TALK199381@talks.cam.ac.uk
CONTACT:James Allingham
DESCRIPTION:We review multi-agent learning\, including equilibrium concept
 s such as Nash equilibrium and correlated equilibrium\, as well as online-
 learning-based algorithms for computing them such as no-regret dynamics. T
 hese techniques were instrumental in the recent breakthrough of human-leve
 l performance in the board game Diplomacy by a computer.\n\nPreparatory re
 ading: Tim Roughgarden\, Twenty Lectures on Algorithmic Game Theory\, Ch. 
 17. https://theory.stanford.edu/~tim/f13/l/l17.pdf 
LOCATION:Cambridge University Engineering Department\, CBL Seminar room BE
 4-38.
END:VEVENT
END:VCALENDAR