[AI Seminar] AI Lunch -- Shayan Doroudi -- March 29, 2016

[Ellen Vitercik]

Dear faculty and students,

We look forward to seeing you this Tuesday, March 29th, at noon in NSH
3305 for AI lunch. To learn more about the seminar and lunch, or to
volunteer to give a talk, please visit the AI Lunch webpage
<http://www.cs.cmu.edu/~aiseminar/>. *We are looking for someone to give a
talk on April 12th.*

On Tuesday, Shayan Doroudi will give a talk titled "Importance Sampling for
Fair Policy Selection."

*Abstract*: Importance sampling is a statistical technique that is used in
batch reinforcement learning settings to give unbiased estimates of how
well a policy will perform given data from another policy. In addition to
evaluating policies, importance sampling has also been used for policy
selection and policy search. In this talk, I show that importance sampling
is unfair when used to choose policies; that is, in some cases it chooses
the worse of two choices more than half of the time. I present several
(possibly counterintuitive) examples of where this unfairness may be of
practical concern. I then show that, in theory, we can make fair decisions
with importance sampling by restricting attention to a particular class of
policies. Using insights gathered from the theory, I present a practical
policy search algorithm that uses importance sampling with a novel form of
regularization.

This is joint work with Emma Brunskill and Phil Thomas.

Best,
Ellen and Ariel
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.srv.cs.cmu.edu/pipermail/ai-seminar-announce/attachments/20160326/722c271c/attachment.html>