UT ML Group: Learning for Planning and Problem Solving

Most learning research concerns classification. Research in learning and planning and problem solving focuses on improving the performance of an AI planning or problem solving system through experience. Our work has focussed on integrating explanation-based learning (EBL) and inductive learning (specifically ILP) to improve the efficiency (speedup learning) and solution-quality for planning and problem solving systems by solving sample problems and learning heuristics that avoid backtracking or sub-optimal solutions.

Our work has focused on two systems:

Publications

  1. Using Multi-Strategy Learning to Improve Planning Efficiency and Quality [Abstract] [PDF]
    Tara A. Estlin
    Ph.D. Thesis, Department of Computer Sciences, University of Texas at Austin, May 1998.
    128 pages
    Also appears as Technical Report AI 98-269, Artificial Intelligence Lab, University of Texas at Austin.

  2. Learning to Improve both Efficiency and Quality of Planning [Abstract] [PDF]
    Tara A. Estlin and Raymond J. Mooney
    Proceedings of the Fifteenth International Joint Conference on Artificial Intelligence (IJCAI-97), pp. 1227-1232, Nagoya, Japan, August 1997.

  3. Integrating Explanation-Based and Inductive Learning Techniques to Acquire Search-Control for Planning [Abstract] [PDF]
    Tara A. Estlin
    Ph.D. proposal, Department of Computer Sciences, University of Texas at Austin, September 1996.
    Also appears as Technical Report AI 96-250, Artificial Intelligence Lab, University of Texas at Austin.

  4. Multi-Strategy Learning of Search Control for Partial-Order Planning [Abstract] [PDF]
    Tara A. Estlin and Raymond J. Mooney
    Proceedings of the Thirteenth National Conference on Artificial Intelligence (AAAI-96), pp. 843-848, Portland, OR, August 1996.

  5. Integrating EBL and ILP to Acquire Control Rules for Planning [Abstract] [PDF]
    Tara A. Estlin and Raymond J. Mooney
    Proceedings of the Third International Workshop on Multi-Strategy Learning (MSL-96), pp. 271-279, Harpers Ferry, WV, May 1996.

  6. Hybrid Learning of Search Control for Partial-Order Planning [Abstract] [PDF]
    Tara A. Estlin and Raymond J. Mooney
    New Directions in AI Planning, M. Ghallab and A. Milani (Eds.), IOS Press, 1996, pp. 129-140.

  7. Integrating ILP and EBL [Abstract] [PDF]
    Raymond J. Mooney and John M. Zelle
    SIGART Bulletin, Volume 5, Number 1, pp. 12-21, January 1994.

  8. Combining FOIL and EBG to Speed-Up Logic Programs [Abstract] [PDF]
    John M. Zelle and Raymond J. Mooney
    Proceedings of the Thirteenth International Joint Conference on Artificial Intelligence (IJCAI-93), pp. 1106-1111, Chambéry, France, July 1993.

  9. Learning Search-Control Heuristics for Logic Programs: Applications to Speedup Learning and Language Acquisition [Abstract] [PDF]
    John M. Zelle
    Ph.D. proposal, Department of Computer Sciences, University of Texas at Austin, March 1993.
    36 pages

  10. Speeding-up Logic Programs by Combining EBG and FOIL [Abstract] [PDF]
    John M. Zelle and Raymond J. Mooney
    Proceedings of the 1992 Machine Learning Workshop on Knowledge Compilation and Speedup Learning, Aberdeen, Scotland, July 1992.

  11. The Effect of Rule Use on the Utility of Explanation-Based Learning [Abstract] [PDF]
    Raymond J. Mooney
    In Proceedings of the Eleventh International Joint Conference on Artificial Intelligence (IJCAI), pp. 725-730, Detroit, MI, August 1989.

  12. Generalizing the Order of Operators in Macro-Operators [Abstract] [PDF]
    Raymond J. Mooney
    In Proceedings of the Fifth International Conference on Machine Learning (ICML), pp. 270-283, Ann Arbor, MI: Morgan Kaufmann, June 1988.

mooney@cs.utexas.edu