BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Probabalistic Inference for solving (PO)MDPs - Finale Doshi (Unive
 rsity of Cambridge)
DTSTART:20090115T140000Z
DTEND:20090115T153000Z
UID:TALK15403@talks.cam.ac.uk
CONTACT:Shakir Mohamed
DESCRIPTION:Recent work has shown that finding a near-optimal policy in an
  MDP or POMDP can be framed as an inference problem.  We will focus on:\n\
 n"Probabilistic inference for solving (PO)MDPs\," Toussaint et. al. (2006)
  \n\nand perhaps talk a little bit about:\n\n"Hierarchical POMDP Controlle
 r Optimization by Likelihood Maximization\," Toussaint et. al. (2008)\n\na
 nd discuss implications for planning and reinforcement learning.
LOCATION:Engineering Department\, CBL Room 438
END:VEVENT
END:VCALENDAR