BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//132.216.98.100//NONSGML kigkonsult.se iCalcreator 2.20.4//
BEGIN:VEVENT
UID:20251225T115634EST-71727to7uE@132.216.98.100
DTSTAMP:20251225T165634Z
DESCRIPTION:Title: Off-Policy Confidence Interval Estimation with Confounde
 d Markov Decision Process.\n\nAbstract: In this talk\, we consider constru
 cting a confidence interval for a target policy’s value offline based on p
 re-collected observational data in infinite horizon settings. Most of the 
 existing works assume no unmeasured variables exist that confound the obse
 rved actions. This assumption\, however\, is likely to be violated in real
  applications such as healthcare and technological industries. We show tha
 t with some auxiliary variables that mediate the effect of actions on the 
 system dynamics\, the target policy’s value is identifiable in a confounde
 d Markov decision process. Based on this result\, we develop an efficient 
 off-policy value estimator that is robust to potential model misspecificat
 ion and provides rigorous uncertainty quantification.\n\n \n\n \n\nZoom: h
 ttps://mcgill.zoom.us/j/83436686293?pwd=b0RmWmlXRXE3OWR6NlNIcWF5d0dJQT09\n
 \nMeeting ID: 834 3668 6293\n\nPasscode: 12345\n\nSite web : https://mcgil
 lstat.github.io\n
DTSTART:20220204T203000Z
DTEND:20220204T213000Z
SUMMARY:Rui Song (North Carolina State University)
URL:/mathstat/channels/event/rui-song-north-carolina-s
 tate-university-337387
END:VEVENT
END:VCALENDAR