PRODIGY: an integrated architecture for planning and learning

ABSTRACT

Artificial intelligence has progressed to the point where multiple cognitive capabilities are being integrated into computational architectures, such as SOAR, PRODIGY, THEO, and ICARUS. This paper reports on the PRODIGY architecture, describing its planning and problem solving capabilities and touching upon its multiple learning methods. Learning in PRODIGY occurs at all decision points and integration in PRODIGY is at the knowledge level; the learning and reasoning modules produce mutually interpretable knowledge structures. Issues in architectural design are discussed, providing a context to examine the underlying tenets of the PRODIGY architecture.

REFERENCES

• 1: Jaime G. Carbonell , Yolanda Gil, Learning by experimentation: the operator refinement method, Machine learning: an artificial intelligence approach volume III, Morgan Kaufmann Publishers Inc., San Francisco, CA, 1990
• 2: Jaime G. Carbonell, Craig A. Knoblock, and Steven Minton. PRODIGY: An integrated architecture for planning and learning. In Kurt VanLehn, editor, <i>Architectures for Intelligence.</i> Erlbaum, Hillsdale, NJ, 1990. Available as Technical Report CMU-CS-89--189.
• 3: Oren Willi Etzioni, A structural theory of explanation-based learning, Carnegie Mellon University, Pittsburgh, PA, 1991
• 4: Oren Etzioni. STATIC: A problem-space compiler for PRODIGY. In <i>Proceedings of the Ninth National Conference on Artificial Intelligence,</i> Anaheim, CA, 1991.
• 5: Robert L. Joseph. Graphical knowledge acquisition. In <i>Proceedings of the Fourth Knowledge Acquisition For Knowledge-Based Systems Workshop,</i> Banff, Canada, 1989.
• 6: Craig Alan Knoblock, Automatically generating abstractions for problem solving, Carnegie Mellon University, Pittsburgh, PA, 1991
• 7: Craig A. Knoblock, Steven Minton, and Oren Etzioni. Integrating abstraction and explanation-based learning in PRODIGY. In <i>Proceedings of the Ninth National Conference on Artificial Intelligence,</i> Anaheim, CA, 1991.
• 8: Pat Langley, Kevin Thompson, Wayne Iba, John H. Gennari, and John A. Allen. An integrated cognitive architecture for autonomous agents. Technical Report 89--28, Department of Information and Computer Science, University of California, Irvine, 1989.
• 9: Steven Minton , Jaime Carbonell, Learning effective search control knowledge: an explanation-based approach, 1988
• 10: S. Minton , J. G. Carbonell , C. A. Knoblock , D. R. Kuokka , O. Etzioni, Explanation-based learning: a problem solving perspective, Artificial Intelligence, v.40 n.1-3, p.63-118, Sep. 1989 [doi>10.1016/0004-3702(89)90047-7]
• 11: Tom M. Mitchell, John Allen, Prasad Chalasani, John Cheng, Oren Etzioni, Marc Ringuette, and Jeffrey C. Schlimmer. Theo: A framework for self-improving systems. In Kurt VanLehn, editor, <i>Architectures for Intelligence.</i> Erlbaum, Hillsdale, NJ, 1990.
• 12: Paul S. Rosenbloom, Allen Newell, and John E. Laird. Towards the knowledge level in SOAR: The role of the architecture in the use of knowledge. In Kurt VanLehn, editor, <i>Architectures for Intelligence.</i> Erlbaum, Hillsdale, NJ, 1990.
• 13: Manuela M. Veloso and Jaime G. Carbonell. Integrating analogy into a general problem-solving architecture. In <i>Intelligent Systems.</i> Ellis Horwood Limited, West Sussex, England, 1990.

INDEX TERMS

Primary Classification:
  C. Computer Systems Organization
  C.1 PROCESSOR ARCHITECTURES
      C.1.3 Other Architecture Styles

Additional Classification:
  I. Computing Methodologies
  I.2 ARTIFICIAL INTELLIGENCE
      I.2.6 Learning
      I.2.8 Problem Solving, Control Methods, and Search
          Subjects: Plan execution, formation, and generation

General Terms:
Design, Performance, Theory