September 13, 2007: Seminar: Leslie Pack Kaelbling: "Learning to Think about the World"

The University of Illinois at Chicago

Department of Computer Science

2007-2008 Distinguished Lecturer Seminar Series

Learning to Think about the World

Leslie Pack Kaelbling
Computer Science and Artificial Intelligence Laboratory (CSAIL)
Massachusetts Institute of Technology

Thursday, September 27, 2007
11:00 a.m., 1000 SEO


In the last 10 years, the combination of techniques from machine learning, statistics, and operations research has allowed major advances in learning and planning for uncertain environments. Reasonably large problems can be solved using current techniques. But what if we want to scale up to the uncertain learning and planning problem that you face every day? It is many orders of magnitude larger than the biggest problem we can solve currently.

In this talk, I'll describe three pieces of work that try to begin to address learning and reasoning in truly huge environments. The first is a method for learning probabilistic rules to describe naive physics models of the interactions between objects. The second is a logical particle filtering method that allows probabilistic state estimation to be carried out in domains with very large or unbounded numbers of individuals. The last is a planning algorithm that tries to find a small planning problem instance within a large domain description, in order to speed up planning for apparently simple problems in very large domains.

Brief Bio:

Leslie Pack Kaelbling is Professor of Computer Science and Engineering and Research Director of the Computer Science and Artificial Intelligence Laboratory (CSAIL) at the Massachusetts Institute of Technology. She has previously held positions at Brown University, the Artificial Intelligence Center of SRI International, and at Teleos Research. She received an A. B. in Philosophy in 1983 and a Ph. D. in Computer Science in 1990, both from Stanford University. Prof. Kaelbling has done substantial research on designing situated agents, mobile robotics, reinforcement learning, and decision-theoretic planning. In 2000, she founded the Journal of Machine Learning Research, a high-quality journal that is both freely available electronically as well as published in archival form; she currently serves as editor-in-chief. Prof. Kaelbling is an NSF Presidential Faculty Fellow, a former member of the AAAI Executive Council, the 1997 recipient of the IJCAI Computers and Thought Award, a trustee of IJCAII and a fellow of the AAAI.

Host: Professor Piotr Gmytrasiewicz

Copyright 2016 The Board of Trustees
of the University of
Helping Women Faculty Advance
Funded by NSF