BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:What can Gaussian Processes do for Reinforcement Learning? - Marc 
 Deisenroth\, Max Planck Institute for Biological Cybernetics\, Tuebingen\,
  Germany
DTSTART:20070524T120000Z
DTEND:20070524T140000Z
UID:TALK7486@talks.cam.ac.uk
CONTACT:Frederik Eaton
DESCRIPTION:After a short introduction to reinforcement learning\, I will 
 talk about possible areas where Gaussian processes can be integrated into 
 the reinforcement learning framework. As a case study\, I will consider th
 e problem of an underactuated pendulum to demonstrate that its swing-up is
  already a difficult task.
LOCATION:5th floor meeting room\, Engineering Department
END:VEVENT
END:VCALENDAR