[Ml-stat-talks] Fwd: Joint CS/CSML Seminar: Shie Mannor (Technion) on Tuesday, October 13 at 12:30pm | Computer Science Room 105

Barbara Engelhardt bee at princeton.edu
Mon Oct 5 15:45:11 EDT 2015


Talk of interest tomorrow.

---------- Forwarded message ----------
From: Esther K. Ruder <estherk at princeton.edu>
Date: Mon, Oct 5, 2015 at 3:34 PM
Subject: Joint CS/CSML Seminar: Shie Mannor (Technion) on Tuesday, October
13 at 12:30pm | Computer Science Room 105
To: CSML-seminars at princeton.edu


Tuesday, October 13, 2015
Computer Science, Room 105
12:30pm
Shie Mannor, Technion – Israel Institute of Technology

Title: Actionable big data: from data to decisions and back

Abstract: In many sequential decision problems all that we have is a record
of historical trajectories. Building dynamic models from these trajectories
and ultimately sequential decision policies may result in much uncertainty
and bias. In this talk we consider the question of how to create control
policies from existing historical data and how to better sample
trajectories so that future control policies would be better. This question
has been central in reinforcement learning in the last decade if not more,
and involves methods from statistics, machine learning, optimization, and
control theory.

I will start my talk with demonstrating why planning with parameter
uncertainty is an important issue. I will then describe several approaches:
Bayesian uncertainty model over the unknown parameters, a robust approach
that takes a worst case view, and a frequentist approach. I will then
discuss the challenges that are posed when the model itself rather than
just the parameters may not be fully known.

I will then describe two challenging real-world domains that have been
studied in my research group in collaboration with experts from industry
and academia: diabetes care management in healthcare and asset management
in high-voltage transmission grids. For each domain I will describe our
efforts to reduce the problem to its bare essentials as a reinforcement
learning problem, the algorithms for learning the control policies, and
some of the lessons we learned.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.cs.princeton.edu/pipermail/ml-stat-talks/attachments/20151005/4ee491cf/attachment.html>


More information about the Ml-stat-talks mailing list