BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//https://caida.ubc.ca//NONSGML iCalcreator 2.41.92//
CALSCALE:GREGORIAN
METHOD:PUBLISH
UID:30306138-3063-4266-b230-333730376137
X-WR-RELCALID:efc09d74-9c93-479e-a94f-485231ddccde
X-WR-TIMEZONE:America/Vancouver
X-WR-CALNAME:Rethinking the Objective for Policy Optimization in Reinforcem
 ent Learning - Martha White\, Associate Professor\, University of Alberta
BEGIN:VTIMEZONE
TZID:America/Vancouver
TZUNTIL:20220313T100000Z
BEGIN:STANDARD
TZNAME:PST
DTSTART:20191103T020000
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
RDATE:20201101T020000
RDATE:20211107T020000
END:STANDARD
BEGIN:DAYLIGHT
TZNAME:PDT
DTSTART:20200308T020000
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
RDATE:20210314T020000
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:ddcb56ed-7388-474a-9439-babee0c03068
DTSTAMP:20260530T145323Z
CLASS:PUBLIC
CREATED:20200529T190730Z
DESCRIPTION:Please register for this event here Abstract: The goal in reinf
 orcement learning is to obtain a policy that maximizes long-term reward. P
 olicy optimization in reinforcement learning involves directly estimating 
 a parameterized policy\, that maps states to probabilities over actions. T
 ypically\, these algorithms are built on the policy gradient theorem\, whi
 ch provides a simple form for the gradient of the policy optimization obje
 ctive. In practice\, however\, a key weighting in the gradient is dropped 
 for convenience\; despite this omission\, these widely used algorithms see
 m to perform quite well…
DTSTART;TZID=America/Vancouver:20200615T153000
DTEND;TZID=America/Vancouver:20200615T163000
LAST-MODIFIED:20210610T230539Z
LOCATION:Please register to receive the Zoom link
SUMMARY:Rethinking the Objective for Policy Optimization in Reinforcement L
 earning - Martha White\, Associate Professor\, University of Alberta
TRANSP:OPAQUE
URL:https://caida.ubc.ca/event/rethinking-objective-policy-optimization-rei
 nforcement-learning-martha-white-associate
END:VEVENT
END:VCALENDAR