Planning and Learning by Analogical/Case-Based Reasoning

(Back to Manuela Veloso's home page.)

I have a long standing interest on planning and learning by reuse of past experience
in the form of cases of planning episodes, following the derivational analogy approach.

I developed Prodigy/Analogy as the main part of my PhD thesis work:

  • Learning by Analogical Reasoning in General Problem Solving,
    School of Computer Science, Carnegie Mellon University, Pittsburgh, PA,
    August 1992, available as technical report CMU-CS-92-174.
    See below the reference to the book publication of my thesis by Springer Verlag.

    For a global view of the Prodigy/Analogy system, check this picture . (You may need to
    swap the landscape orientation of the picture depending on your ghostviewer settings.)

    Prodigy/Analogy is now being released on an experimental basis with the Prodigy-UI .
    The code released consists mainly of the storage and replay procedures.
    There is not a specific manual available. The user should be able to follow the Prodigy-UI easily.

    Recently we have been applying Prodigy/Analogy to planning in realistic applications.
    See the publications in route planning by analogy with Karen Haigh.

    SOME PUBLICATIONS:
    (Send email (veloso@cs.cmu.edu) if you are interested in these or any other specific ones.)

  • Planning and Learning by Analogical Reasoning
    Manuela Veloso
    Springer Verlag, December 1994.
    (This is a book publication of my PhD thesis document.)

  • Derivational Analogy in PRODIGY: Automating Case Acquisition, Storage, and Utilization
    Manuela M. Veloso and Jaime G. Carbonell
    Machine Learning, 10, 249-278, 1993.

  • Flexible Strategy Learning: Analogical Replay of Problem Solving Episodes
    Manuela Veloso
    Proceedings of Twelfth National Conference on Artificial Intelligence,
    AAAI Press, 1994, 595-600.

  • Prodigy/Analogy: Analogical Reasoning in General Problem Solving
    Manuela M. Veloso
    Topics in Case-Based Reasoning,
    S. Wess, K.-D. Althoff, and M. Richter (eds.), Springer Verlag, 1994, 33-50.

  • Case-Based Reasoning in PRODIGY
    Manuela M. Veloso and Jaime G. Carbonell
    Machine Learning: A Multistrategy Approach, Volume IV,
    R. S. Michalski and G. Teccuci (eds), Morgan Kaufmann, 1994, 523-548.

  • Towards Scaling Up Machine Learning: A Case Study with Derivational Analogy in PRODIGY
    Manuela M. Veloso and Jaime G. Carbonell
    Machine Learning Methods for Planning,
    S. Minton (ed), Morgan Kaufmann, 1993, 233-272.