Efficient Model Learning for Reinforcement Learning
Speaker: Michael Littman , Rutgers University, Department of Computer Science
Date: May 18 2007
Time: 3:00PM to 4:00PM
Location: Star, 32-D463
Host: Professor Leslie Kaelbling, MIT CSAIL
Contact: Teresa Cataldo, 617-452-5005, cataldo@csail.mit.edu
Relevant URL: Abstract:
This talk addresses the problem of learning efficiently to make sequential decisions with a particular focus on generalizing experience without forfeiting formal learning-time guarantees. I'll summarize the theoretically motivated algorithms my group has been developing that exhibit practical advantages over existing learning algorithms. I'll also toss in some video footage of robots learning to move around by exploring efficiently.
See other events that are part of Language, Learning, Vision and Graphics Seminar Series (LLVG) 2006/2007
See other events happening in May 2007
