BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Deep reinforcement learning for dialogue policy optimisation - Dr 
 Milica Gasic\, Dept. Engineering\, University of Cambridge
DTSTART:20180216T120000Z
DTEND:20180216T130000Z
UID:TALK99475@talks.cam.ac.uk
CONTACT:Andrew Caines
DESCRIPTION:In spoken dialogue systems\, we aim to deploy artificial intel
 ligence to build automated dialogue agents that can converse with humans. 
 As part of this effort\, we need to find ways to optimise the dialogue pol
 icy\, i.e. we need to optimise a function that takes the current state of 
 the dialogue as input and returns the response of the system. This is norm
 ally done via reinforcement learning. Deep reinforcement learning approach
 es have produced state-of-the-art results on games. In this talk I will di
 scuss the necessary steps needed to deploy deep reinforcement learning for
  dialogue policy optimisation. I will also discuss the necessity for commo
 n benchmarks and the efforts in the Dialogue Systems Group to provide thes
 e.
LOCATION:FW26\, Computer Laboratory
END:VEVENT
END:VCALENDAR