Amy McGovern Assistant Professor, School of Computer Science Adjunct Assistant Professor, School of Meteorology Director, IDEA lab University of Oklahoma Office: EL 144A Phone: 405-325-5427

Research Interests

My research focuses on using machine learning techniques to enable greater autonomy in agents, with a particular interest in robotics as related to space exploration. Specific areas of interest include:

• Autonomous discovery of structure. My dissertation focused on autonomously identifying and creating useful temporal abstractions from an agent's interaction with its environment. Current work focuses on identifying structure in relational learning tasks using knowledge discovery and data mining approaches.
• Knowledge representation. How can we efficiently represent the knowledge learned in one task and reuse it for other tasks? This knowledge can take the form of a control policy learned to solve one task or a representation of structure in an environment.
• Interaction of reinforcement learning, supervised learning, and relational learning methods. I am particularly interested in the combined use of these techniques to create more robust and autonomous learning systems.
• Robotics and space Application of these techniques to robots, with a particular focus on robots assisting a human presence in space.

I direct the Interaction, Discovery, Exploration and Adaptation (IDEA) lab. You can find more information on our research from the lab web page.

Education

• Ph.D. in Computer Science (May 2002), University of Massachusetts Amherst. Dissertation: Autonomous Discovery of Temporal Abstractions from Interaction with an Environment
  Committee: Andrew G. Barto (chair), J. Eliot B. Moss, Roderic Grupen, and Neil Berthier
• M.S. in Computer Science (1998), University of Massachusetts Amherst.
• B.S. (Honors) in Math and Computer Science (minor: Spanish), Carnegie Mellon University.

My other pages

[Publications] [Courses]

Links