BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Universal Bayesian Agents: Theory and Applications - Prof. Marcus 
 Hutter (ANU)
DTSTART:20110118T110000Z
DTEND:20110118T120000Z
UID:TALK28874@talks.cam.ac.uk
CONTACT:Zoubin Ghahramani
DESCRIPTION:The dream of creating artificial devices that reach or\noutper
 form human intelligence is many centuries old. In this\ntalk I present an 
 elegant parameter-free theory of an optimal\nreinforcement learning agent 
 embedded in an arbitrary unknown\nenvironment that possesses essentially a
 ll aspects of rational\nintelligence. The theory reduces all conceptual AI
  problems to\npure computational questions. The necessary and sufficient\n
 ingredients are Bayesian probability theory\; algorithmic\ninformation the
 ory\; universal Turing machines\; the agent\nframework\; sequential decisi
 on theory\; and reinforcement\nlearning\, which are all important subjects
  in their own right.\nI also present some recent approximations\, implemen
 tations\, and\napplications of this modern top-down approach to AI.
LOCATION:Engineering Department\, CBL Room 438
END:VEVENT
END:VCALENDAR