BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Policy Gradient Methods in Repeated Games Joint work with Domenico
  Mergoni and Ed Plumb
DTSTART:20251030T103000
DTEND:20251030T113000
DTSTAMP:20260407T141523Z
UID:32b94d06221b2255b02748c0f79fd966bc38234754be378fb0d799db
CATEGORIES:Conferences - Seminars
DESCRIPTION:Dr Galit Ashkenazi-Golan\, Assistant Professor at the departme
 nt of mathematics\, LSE\, UK\nAbstract:\nPolicy gradient methods have emer
 ged as powerful tools for optimising complex decision-making processes.\nT
 hese methods utilise gradient ascent to iteratively enhance policies based
  on observed rewards.\nWhile they frequently achieve local convergence\, g
 lobal convergence guarantees remain elusive outside of specific classes of
  games.\nWe illustrate this phenomenon through examples\, illuminating the
  challenges surrounding global optimisation.\nFollowing that\, we explore 
 the utilisation of policy gradient methods in repeated games and define th
 e set of policies that are learnable using these methods.\nLastly\, we pro
 vide a preview of our follow-up presentation\, wherein we will present a F
 olk theorem result for learning in repeated games.\n\n \nShort Bio\nGalit
  Ashkenazi-Golan is an assistant professor at the department of mathematic
 s\, London School of Economics and Political Science (LSE)\, United Kingdo
 m.\nHer PhD is from the school of mathematical sciences – Tel-Aviv Unive
 rsity\, and she spent more than two years being a visiting student at the 
 Ecole Polytechnique\, Paris.\nHer topics of research are repeated games\, 
 stochastic games\, opinion dynamics and learning in games.\nRecently\, she
  has focused on the game dynamics resulting from multi-agent reinforcement
  learning.
LOCATION:ME C2 405 https://plan.epfl.ch/?room==ME%20C2%20405
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR