BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Efficient stochastic optimal control for navigation and motor plan
 ning - Bert Kappen\, Radboud University Nijmegen\, The Netherlands
DTSTART:20070711T100000Z
DTEND:20070711T110000Z
UID:TALK7631@talks.cam.ac.uk
CONTACT:Taylan Cemgil
DESCRIPTION:This talk discusses a class of non-linear stochastic control p
 roblems that can be efficiently solved using a path integral. In this cont
 rol formalism\, the central concept of cost-to-go or value function become
 s a free energy and methods and concepts from statistical physics can be r
 eadily applied\, such as Monte Carlo sampling or the Laplace approximation
 . \nQualitatively different optimal control strategies for different noise
  levels can be understood as a result of spontaneous symmetry breaking. Wh
 en applied to a receding horizon problem in a stationary environment\, the
  solution resembles the one obtained by traditional reinforcement learning
  with discounted reward. An advantage of the path integral control method 
 over RL is that the control can be computed for the current state\, withou
 t considering all other states and 2) that it can be easily generalized to
  time-dependent tasks. It is therefore a suitable approach for time depend
 ent control. We further discuss exploration and an how agents can approxim
 ately compute their coordination using belief propagation.\n
LOCATION:LR6\, Engineering\, Department of
END:VEVENT
END:VCALENDAR