BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//https://caida.ubc.ca//NONSGML iCalcreator 2.41.92//
CALSCALE:GREGORIAN
METHOD:PUBLISH
UID:65646366-3030-4134-a164-356538303463
X-WR-RELCALID:efc09d74-9c93-479e-a94f-485231ddccde
X-WR-TIMEZONE:America/Vancouver
X-WR-CALNAME:The Provable Effectiveness of Policy Gradient Methods in Reinf
 orcement Learning and Controls - Sham Kakade\, Professor\, University of W
 ashington\; Microsoft Research
BEGIN:VTIMEZONE
TZID:America/Vancouver
TZUNTIL:20231105T090000Z
BEGIN:STANDARD
TZNAME:PST
DTSTART:20201101T020000
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
RDATE:20211107T020000
RDATE:20221106T020000
END:STANDARD
BEGIN:DAYLIGHT
TZNAME:PDT
DTSTART:20210314T020000
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
RDATE:20220313T020000
RDATE:20230312T020000
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:77249717-23e9-46dd-ba94-307fa6799896
DTSTAMP:20260429T133051Z
CLASS:PUBLIC
CREATED:20210909T212713Z
DESCRIPTION:Please register for this event here. Abstract: Reinforcement le
 arning is the dominant paradigm for how an agent learns to interact with t
 he world in order to achieve some long term objectives. Here\, policy grad
 ient methods are among the most effective methods in challenging reinforce
 ment learning problems\, due to that they: are applicable to any different
 iable policy parameterization\; admit easy extensions to function approxim
 ation\; easily incorporate structured state and action spaces\; are easy t
 o implement in a simulation based\, model-free manner. However\, little is
  known about even their…
DTSTART;TZID=America/Vancouver:20210927T130000
DTEND;TZID=America/Vancouver:20210927T140000
LAST-MODIFIED:20210909T214657Z
LOCATION:Please register to receive the Zoom link
SUMMARY:The Provable Effectiveness of Policy Gradient Methods in Reinforcem
 ent Learning and Controls - Sham Kakade\, Professor\, University of Washin
 gton\; Microsoft Research
TRANSP:OPAQUE
URL:https://caida.ubc.ca/event/provable-effectiveness-policy-gradient-metho
 ds-reinforcement-learning-and-controls-sham
END:VEVENT
END:VCALENDAR