[Colloquium] John Langford talk 10/9 at TTI-C
Meridel Trimble
mtrimble at tti-c.org
Tue Oct 7 16:44:37 CDT 2003
TOYOTA TECHNOLOGICAL INSTITUTE TALK
Speaker: John Langford
Toyota Technological Institute at Chicago
Speakers homepage: http://www.tti-c.org/langford.shtml
Date: Thursday, October 9th, 2003
Time: 12:15pm
Place: TTI-Cs Conference Room (The Press Building - 1427 E. 60th St.)
FREE LUNCH WILL BE PROVIDED
Title: Robust Approximate Reinforcement Learning
Abstract: In the "real world" the space of an agents' states or observations is
not practically enumerable, implying that exact algorithms to optimize an
agents expected reward are impractical. One common solution is to derive
approximate forms of the exact algorithms, such as approximate policy
iteration. Unfortunately, these approaches tend to be nonrobust since the
sample complexity (or number of interactions with the world) required to
guarantee success remains proportional to the size of the state space.Another
solution (currently being pursued by many people) is to reduce reinforcement
learning to classification, for which many algorithms and performance
guarantees are not explicitly or even implicitly dependent on the size of a
state space. I will discuss how to do this, what theoretical guarantees can be
transferred from classification, and show some empirical results suggesting
this approach works well in practice.
Please contact Meridel Trimble for further information
(mtrimble at tti-c.org/773.834.9873)
More information about the Colloquium
mailing list