[Colloquium] TTI-C Talk, Pierre Tarres 4/5/05 @ 3pm

[Katherine Cumming]

TOYOTA TECHNOLOGICAL INSTITUTE TALK 
Schedule Change
Learning Theory Program
Speaker:  Pierre Tarres, University of Paul-Sabatier
Speaker's homepage:  http://www.lsp.ups-tlse.fr/Fp/Tarres/ 
Original Time:  Wednesday, March 23rd, 2005 @ 3:00pm
Moved To:      Tuesday, April 5th, 2005 @ 3:00pm
Location:  TTI-C Conference Room 
Title: Stochastic Algorithms and Learning 
Abstract:
We discuss the asymptotic behavior of some stochastic algorithms arising
in learning and self-organization. First we introduce some new results
on the two-armed bandit problem, interpret them in terms of stochastic
approximation of an underlying dynamical system, and explain how the
methods in this framework adapt to other questions in reinforcement
learning in games and generalized urn models. Then we present some
problems related to self-organization appearing in reinforcement on
graphs, whose study requires a combination of stochastic approximation
and Markov chain methods. 
 
 
 
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://mailman.cs.uchicago.edu/pipermail/colloquium/attachments/20050321/cf4b44b8/attachment.htm