Computer Science - Duke University

Ronald Parr

Associate Professor of Computer Science

Faculty Group: Artificial Intelligence

Email	parr at cs.duke.edu
Office	D209 LSRC
Phone	(919) 660-6537
Fax	(919) 660-6519
Web page	http://www.cs.duke.edu/~parr

Education

Ph.D., University of California, Berkeley, 1998
A.B., (cum laude) Princeton University, 1990

Honors & Awards

IJCAI-JAIR Best Paper Award, "Efficient Solution Algorithms for Factored MDPs," 2007; Alfred P. Sloan Fellowship, 2003; Best Student Paper Award, "Inference in Hybrid Networks: Theoretical Limits and Practical Algorithms," UAI, 2001 with Uri Lerner (student first author).

Research

Reasoning under uncertainty, Markov decision processes, Reinforcement learning, Bayesian networks, and Robotics.

Selected Publications

"An Analysis of Linear Models, Linear Value-Function Approximation, and Feature Selection for Reinforcement Learning," Ronald Parr, Lihong Li, Gavin Taylor, Christopher Painter-Wakefield, and Michael L. Littman, International Conference on Machine Learning (ICML-2008).
"Hierarchical Linear/Constant Time SLAM using Particle Filters for Dense Maps," Austin I. Eliazar and Ronald Parr, Advances in Neural Information Processing Systems (NIPS-19) 2005.
"Least-Squares Policy Iteration," Michail Lagoudakis and Ronald Parr, Journal of Machine Learning Research (JMLR), Vol. 4, 2003, pp. 1107-1149.
"Efficient Solution Algorithms for Factored MDPs," Carlos Guestrin, Daphne Koller, Ronald Parr and Shobha Venkataraman, Journal of Artificial Intelligence Research (JAIR), Vol. 19, 2003, pp. 399-468.
"Coordinated Reinforcement Learning," Carlos Guestrin, Michail Lagoudakis,and Ronald Parr. Nineteenth International Conference on Machine Learning (ICML-2002), pp. 227-234, July 2002.

Extended List of Publications

Publications by Ronald Parr