Alicia Pérez

Graduated student


Some useful and interesting links (to AI research, Spain, fun and entertainment).

Research Interests

I do research on artificial intelligence, in particular on planning and machine learning, and their combination. Research on AI planning designs, develops, and analyzes computer programs that generate sequence of actions that an agent (for example a robot or the machines in a machine shop) must follow in order to achieve a goal. Machine Learning for planning systems builds programs that improve the performance of planners, by increasing their efficiency (building plans faster), by increasing the quality of the plans (according to some problem-dependent quality metric), or by developing and refining the planner's model of the actions available in the world. In particular I use Prodigy: an AI planning and learning system developed at Carnegie Mellon as a research testbed.
I finished my PhD from Carnegie Mellon University, School of Computer Science in July 1996. Here you can find an abstract of my PhD thesis on Learning search control knowledge to improve plan quality.

Recent Publications

  • Representing and Learning Quality-Improving Search Control Knowledge
    M. Alicia Pérez.
    In Lorenza Saitta, ed., Machine Learning: Proceedings of the Thirteenth International Conference, Morgan Kaufmann Publishers, San Francisco, CA. 1996.

  • Learning from a Domain Expert to Generate Good Plans
    M. Alicia Pérez.
    In Acquisition, Learning and Demonstration: Automating Tasks for Users. Papers from the 1996 AAAI Symposium. March 1996, Stanford, CA. Technical Report SS-96-02. AAAI Press. Menlo Park, CA.

  • Learning Search Control Knowledge to Improve Plan Quality.
    M. Alicia Pérez.
    PhD thesis, available as Technical Report CMU-CS-95-175, School of Computer Science, Carnegie Mellon University, July 1995.

  • Integrating Planning and Learning: The PRODIGY Architecture.
    Manuela Veloso, Jaime Carbonell, M. Alicia Pérez, Daniel Borrajo, Eugene Fink and Jim Blythe.
    Journal of Experimental and Theoretical Artificial Intelligence, Vol. 7, number 1, January 1995.

  • Control Knowledge to Improve Plan quality.
    M. Alicia Pérez and Jaime Carbonell.
    In Proceedings of the Second International Conference on AI Planning Systems, AIPS-94, pages 323--328, Chicago, IL, June 1994. AAAI Press.

  • Applying a general-purpose planning and learning architecture to process planning.
    Yolanda Gil and M. Alicia Pérez.
    In Working Notes of the AAAI 1994 Fall Symposium Series, Symposium on Planning and Learning: On to Real Applications, pages 48--52, New Orleans, November 1994.
  • Extended list of publications