BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Inverse reinforcement learning for modeling micro-turn taking - Do
 ngho Kim
DTSTART:20140110T120000Z
DTEND:20140110T130000Z
UID:TALK49770@talks.cam.ac.uk
CONTACT:Rogier van Dalen
DESCRIPTION:Inverse reinforcement learning (IRL) is a technique for recove
 ring a decision-making agent’s underlying reward function by observing i
 ts behaviour in interaction with a specific environmental model. The signi
 ficance of IRL stems from its ability to solve problems in a diverse range
  of research areas where an agent’s behavior can be characterised by a r
 eward function which reflects the agent’s objective and preferences. In 
 this talk\, we present an application of IRL to micro-turn interaction ana
 lysis\, aiming at identifying the conversational agent’s objective in th
 e turn-taking behavior and developing a micro-turn manager for incremental
  dialogue systems.
LOCATION:Department of Engineering - LR6
END:VEVENT
END:VCALENDAR