RL4: A Tool for Knowledge-Based Induction

  • Scott Clearwater
  • Foster Provost

The importance of knowledge-based induction programs for problem solving is discussed.  Desiderata for knowledge-based induction programs are given, and an example of such a program in the context learning classifications is discussed.  The induction program RL4 is used as an induction tool, and several examples of its past and present uses are presented.  The power of the tool comes from its flexibility and ease of use with a performance system.  The use of RL4 with an inference engine that uses user-defined or default evidence gathering strategies is also discussed.  Finally, the directions in which RL4 can go in the future are considered.