BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Search methods based on Monte-Carlo simulation - Martin Müller\, 
 University of Alberta
DTSTART:20100805T130000Z
DTEND:20100805T140000Z
UID:TALK25750@talks.cam.ac.uk
CONTACT:Microsoft Research Cambridge Talks Admins
DESCRIPTION:Search methods based on Monte-Carlo simulation have revolution
 ized difficult game-playing domains such as Go and General Game Playing. M
 onte-Carlo Random Walk planning applies Monte-Carlo ideas to deterministic
  classical planning. The forward chaining planner Arvand uses such Monte-C
 arlo random walks to explore the local neighborhood of a search state for 
 action selection. Random walks yield a large unbiased sample of the search
  neighborhood\, and require expensive state evaluations only at the endpoi
 nts of each walk. The result is a relatively simple but powerful planner t
 hat is competitive with state of the art systems. The talk introduces the 
 main ideas of planning using Monte-Carlo random walks\, and briefly discus
 ses recent work to improve plan quality and to improve planning with limit
 ed resources. 
LOCATION:Small public lecture room\, Microsoft Research Ltd\, 7 J J Thomso
 n Avenue (Off Madingley Road)\, Cambridge
END:VEVENT
END:VCALENDAR