BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Reinforcement Learning and Control as Probabilistic Inference - Ro
 bert Pinsler\, Calvin Kao
DTSTART:20181031T140000Z
DTEND:20181031T153000Z
UID:TALK114334@talks.cam.ac.uk
CONTACT:75379
DESCRIPTION:Reinforcement learning and inference offer powerful  framework
 s for solving sequential decision-making problems. While classically reinf
 orcement learning and inference have been studied independently\, it is po
 ssible to frame the decision-making problem itself as inference in a graph
 ical model. This formalism allows us to utilize well-known approximate inf
 erence techniques and gives insights into how we can extend the model. The
  basic underlying framework has been proposed in the literature in several
  forms before\, and remains an important source\nof inspiration for novel 
 algorithms.
LOCATION:Engineering Department\, CBL Room 438
END:VEVENT
END:VCALENDAR