BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Drupal iCal API//EN
X-WR-CALNAME:Events items teaser
X-WR-TIMEZONE:America/Toronto
BEGIN:VTIMEZONE
TZID:America/Toronto
X-LIC-LOCATION:America/Toronto
BEGIN:DAYLIGHT
TZNAME:EDT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
DTSTART:20060402T070000
END:DAYLIGHT
BEGIN:STANDARD
TZNAME:EST
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
DTSTART:20061029T060000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
UID:69b6febcec72f
DTSTART;TZID=America/Toronto:20070112T113000
SEQUENCE:0
TRANSP:TRANSPARENT
DTEND;TZID=America/Toronto:20070112T113000
URL:https://uwaterloo.ca/artificial-intelligence-group/events/ai-seminar-au
 tomated-hierarchy-discovery-planning-partially
LOCATION:DC - William G. Davis Computer Research Centre 200 University Aven
 ue West 2306C (AI lab) Waterloo ON N2L 3G1 Canada
SUMMARY:AI seminar: Automated hierarchy discovery for planning in partially
 \nobservable domains
CLASS:PUBLIC
DESCRIPTION:Speaker: Laurent Charlin\n\nPlanning in partially observable do
 mains is a notoriously difficult\nproblem. However\, in many real-world sc
 enarios\, planning can be\nsimplified by decomposing the task into a hiera
 rchy of smaller\nplanning problems. Several approaches have been proposed 
 to optimize a\npolicy that decomposes according to a hierarchy specified a
  priori. In\nthis thesis\, I investigate the problem of automatically disc
 overing\nthe hierarchy.
DTSTAMP:20260315T184724Z
END:VEVENT
END:VCALENDAR