BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//talks.cam.ac.uk//v3//EN
BEGIN:VTIMEZONE
TZID:Europe/London
BEGIN:DAYLIGHT
TZOFFSETFROM:+0000
TZOFFSETTO:+0100
TZNAME:BST
DTSTART:19700329T010000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=-1SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0100
TZOFFSETTO:+0000
TZNAME:GMT
DTSTART:19701025T020000
RRULE:FREQ=YEARLY;BYMONTH=10;BYDAY=-1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
CATEGORIES:CUED Speech Group Seminars
SUMMARY:Inverse reinforcement learning for modeling micro-
 turn taking - Dongho Kim
DTSTART;TZID=Europe/London:20140110T120000
DTEND;TZID=Europe/London:20140110T130000
UID:TALK49770AThttp://talks.cam.ac.uk
URL:http://talks.cam.ac.uk/talk/index/49770
DESCRIPTION:Inverse reinforcement learning (IRL) is a techniqu
 e for recovering a decision-making agent’s underly
 ing reward function by observing its behaviour in 
 interaction with a specific environmental model. T
 he significance of IRL stems from its ability to s
 olve problems in a diverse range of research areas
  where an agent’s behavior can be characterised by
  a reward function which reflects the agent’s obje
 ctive and preferences. In this talk\, we present a
 n application of IRL to micro-turn interaction ana
 lysis\, aiming at identifying the conversational a
 gent’s objective in the turn-taking behavior and d
 eveloping a micro-turn manager for incremental dia
 logue systems.
LOCATION:Department of Engineering - LR6
CONTACT:Rogier van Dalen
END:VEVENT
END:VCALENDAR