BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//wp-events-plugin.com//7.2.3.1//EN
TZID:Europe/Paris
X-WR-TIMEZONE:Europe/Paris
BEGIN:VEVENT
UID:8530@i2m.univ-amu.fr
DTSTART;TZID=Europe/Paris:20250108T103000
DTEND;TZID=Europe/Paris:20250108T120000
DTSTAMP:20250109T131500Z
URL:https://www.i2m.univ-amu.fr/evenements/risk_sensitive_reinforcement_le
 arning/
SUMMARY:Alexandre Marthe (ENS Lyon\, UMPA): Risk Sensitive Reinforcement Le
 arning
DESCRIPTION:Alexandre Marthe: Reinforcement Learning (RL) provides a framew
 ork for sequential decision-making under uncertainty\, grounded in Markov 
 Decision Processes (MDPs) and dynamic programming principles. This talk be
 gins by reviewing the core concepts of RL\, including MDPs\, the Bellman e
 quation\, and classical algorithms for finding optimal policies.\n\nIn the
  second part\, we shift the focus to risk-sensitive objectives. While stan
 dard RL maximizes expected returns\, many real-world applications must acc
 ount for variability and worst-case outcomes. We therefore introduce risk 
 measures (e.g.\, Value at Risk or Conditional Value at Risk\, Entropic Ris
 k Measure) and discuss how incorporating them alters the Bellman equation 
 and challenges existing theoretical guarantees.
CATEGORIES:Séminaire,Doctorant⋅es de l'I2M
LOCATION:Saint-Charles - FRUMAM  (2ème étage)\, 3 Place Victor Hugo\, Mar
 seille\, 13003\, France
X-APPLE-STRUCTURED-LOCATION;VALUE=URI;X-ADDRESS=3 Place Victor Hugo\, Marse
 ille\, 13003\, France;X-APPLE-RADIUS=100;X-TITLE=Saint-Charles - FRUMAM  (
 2ème étage):geo:0,0
END:VEVENT
BEGIN:VTIMEZONE
TZID:Europe/Paris
X-LIC-LOCATION:Europe/Paris
BEGIN:STANDARD
DTSTART:20241027T020000
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
END:STANDARD
END:VTIMEZONE
END:VCALENDAR