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:20190310T070000
END:DAYLIGHT
BEGIN:STANDARD
TZNAME:EST
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
DTSTART:20181104T060000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
UID:69b6132932143
DTSTART;TZID=America/Toronto:20190517T140000
SEQUENCE:0
TRANSP:TRANSPARENT
DTEND;TZID=America/Toronto:20190517T140000
URL:https://uwaterloo.ca/artificial-intelligence-group/events/masters-essay
 -presentation-deep-reinforcement-learning
LOCATION:DC - William G. Davis Computer Research Centre 200 University Aven
 ue West 3102 Waterloo ON N2L 3G1 Canada
SUMMARY:Master’s Essay Presentation: Deep Reinforcement Learning with\nDe
 creasing Smoothing ParameterExport this event to calendar
CLASS:PUBLIC
DESCRIPTION:YINGLUO XUN\, MASTER’S CANDIDATE\n_David R. Cheriton School o
 f Computer Science_\n\nIn reinforcement learning\, entropy-regularized val
 ue function (in\npolicy space) has attracted a lot of attention recently d
 ue to its\neffect on smoothing the value function\, and the effect on enco
 uraging\nexploration. However\, there is a discrepancy between the regular
 ized\nobjective function and the original objective function in existing\n
 methods\, which would potentially result in a discrepancy between the\ntra
 ined policy and the optimal policy\, as the policy directly depends\non th
 e value function in the reinforcement learning framework. 
DTSTAMP:20260315T020217Z
END:VEVENT
END:VCALENDAR