BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Of Uncertain Value -- Bayesian Quadratic Reinforcement Learning - 
 Philipp Hennig (University of Cambridge)
DTSTART:20090929T100000Z
DTEND:20090929T110000Z
UID:TALK19696@talks.cam.ac.uk
CONTACT:Emli-Mari Nel
DESCRIPTION:How much do you need to know about the future to take the righ
 t decisions?\n\nIn this talk\, I will briefly review two influential recen
 t works in Bayesian Reinforcement Learning\, and then move on to my own wo
 rk in progress\, on an attempt to find a good Gaussian approximation to th
 e Bellman posterior over values. Unfortunately\, the "right" Gaussian fit 
 turns out to be very difficult to track\, but a simplistic approximation g
 ives surprisingly good results. Preliminary experiments suggest that this 
 approach compares favorably to contemporary Reinforcement Learning algorit
 hms.
LOCATION:TCM Seminar Room\, Cavendish Laboratory\, Department of Physics
END:VEVENT
END:VCALENDAR