Amy McGovern

RESEARCH INTERESTS

Artificial intelligence, machine learning, reinforcement learning, relational knowledge discovery, data mining and robotics.

BIOGRAPHY

Dr. Amy McGovern is an assistant professor in the School of Computer Science at the University of Oklahoma. Her education includes: PhD in Computer Science in 2002 from the University of Massachusetts Amherst, MS in Computer Science in 1998 from the University of Massachusetts Amherst and BS (Honors) in Math and Computer Science (minor: Spanish) from Carnegie Mellon University in 1996. From 2002 to 2004, Dr. McGovern was a Senior Postdoctoral Research Associate in the Knowledge Discovery Laboratory at the University of Massachusetts Amherst where her research focused on methods to discover predictive structures using a relational representation. While there, the team she led captured first place for the open task of the annual Knowledge Discovery and Data Mining competition (KDD Cup) in 2003. Dr. McGovern's research focuses on creating intelligent agents by developing and using methods from artificial intelligence, machine learning, knowledge discovery, data mining, and robotics that enable autonomous discovery of useful structure, patterns, and abstractions from an agent's interaction with its environment. She has a particular interest in applications that will enable humans to safely live long-term in space.

SELECTED PUBLICATIONS

McGovern, Amy , Andrew G. Barto, and Moss, J. Eliot B. (in preparation) Identifying Action Sequences to Facilitate Knowledge Transfer.

McGovern, Amy, Friedland, Lisa, Hay, Michael, Gallagher, Brian, Fast, Andrew, Neville, Jennifer, and Jensen, David (2003) Exploiting Relational Structure to Understand Publication Patterns in High-Energy Physics, Knowledge Discovery Laboratory, University of Massachusetts Amherst. (2003). SIGKDD Explorations, December 2003, Volume 5, Issue 2, pages 165-172. Winning entry to the open task for KDD Cup.

McGovern, Amy and Jensen, David. (2003) Identifying Predictive Structures in Relational Data Using Multiple Instance Learning. Proceedings of the 20th International Conference on Machine Learning, pages 528-535.

Blau, Hannah and McGovern, Amy . (2003) Categorizing Unsupervised Relational Learning Algorithms. For the Workshop on Learning Statistical Models from Relational Data at International Joint Conference on Artificial Intelligence

McGovern, Amy , and Jensen, David (2003) Chi squared: a simpler evaluation function for multiple-instance learning. University of Massachusetts, Amherst Technical Report 03-14.

McGovern, Amy , Moss, Eliot, and Andrew G. Barto (2002) Building a Basic Block Instruction Scheduler using Reinforcement Learning and Rollouts, Machine Learning, Special Issue on Reinforcement Learning. Volume 49, Numbers 2/3, Pages 141-160.

McGovern, Amy , and Barto, Andrew G. (2001) Automatic Discovery of Subgoals in Reinforcement Learning using Diverse Density. Proceedings of the 18th International Conference on Machine Learning, pages 361-368.

McGovern, Amy , and Moss, Eliot, and Barto, Andrew G. (1999) Scheduling Straight-Line Code Using Reinforcement Learning and Rollouts. University of Massachusetts, Amherst Technical Report 99-23.

McGovern, Amy, and Fager, Jason. (2007) Creating Significant Learning Experiences in Introductory Artificial Intelligence. Proceedings of SIGCSE 2007, technical symposium on computer science education, pages 39-43.

McGovern, Amy, and Rosendahl, Derek H., and Kruger, Adrianna, and Beaton, Meredith G., and Brown, Rodger A., and Droegemeier, Kelvin K. (2007) Understanding the formation of tornadoes through data mining. Preprints of the Fifth Conference on Artificial Intelligence and its Applications to Environmental Sciences at the American Meteorological Society annual conference.

Dabney, William, and McGovern, Amy (2007) Utile Distinctions for Relational Reinforcement Learning. Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI-07), pages 738-743.

McGovern, Amy, Friedland, Lisa, Hay, Michael, Gallagher, Brian, Fast, Andrew, Neville, Jennifer, and Jensen, David (2003) Exploiting Relational Structure to Understand Publication Patterns in High-Energy Physics, Knowledge Discovery Laboratory, University of Massachusetts Amherst. (2003). SIGKDD Explorations, December 2003, Volume 5, Issue 2, pages 165-172. Winning entry to the open task for KDD Cup.

McGovern, Amy , Moss, Eliot, and Andrew G. Barto (2002) Building a Basic Block Instruction Scheduler using Reinforcement Learning and Rollouts, Machine Learning, Special Issue on Reinforcement Learning. Volume 49, Numbers 2/3, Pages 141-160.

McGovern, Amy , and Jensen, David (2003) Identifying Predictive Structures in Relational Data Using Multiple Instance Learning. Proceedings of the 20th International Conference on Machine Learning, pages 528-535.