Home | Publications | CS Home

Uncertainty Based Selection of Learning Experiences


Paul Scott and Shaul Markovitch. Uncertainty Based Selection of Learning Experiences. In Proceedings of The Sixth International Workshop on Machine Learning, 358-361 Ithaca, New York, 1989.Morgan Kaufmann


Abstract

The training experiences needed by a learning system may be selected by either an external agent or the system itself. We show that knowledge of the current state of the learner's representation, which is not available to an external agent, is necessary for selection of informative experiences. Hence it is advantageous if a learning system can select its own experiences. We show that the uncertainty of the current representation can be used as a heuristic to guide selection of experiences, and describe results obtained with DIDO, an inductive learning system we have developed using an uncertainty based selection heuristic.


Keywords: Active Learning, Selective Learning, Relational Reinforcement Learning, Exploration
Secondary Keywords:
Online version:
Bibtex entry:
 @inproceedings{Scott:1989:UBS,
  Author = {Paul Scott and Shaul Markovitch},
  Title = {Uncertainty Based Selection of Learning Experiences},
  Year = {1989},
  Booktitle = {Proceedings of The Sixth International Workshop on Machine Learning},
  Pages = {358--361},
  Address = {Ithaca, New York},
  Url = {http://www.cs.technion.ac.il/~shaulm/papers/pdf/Scott-Markovitch-icml1989.pdf},
  Keywords = {Active Learning, Selective Learning, Relational Reinforcement Learning, Exploration},
  Secondary-keywords = {Exploratory Learning},
  Abstract = {
    The training experiences needed by a learning system may be
    selected by either an external agent or the system itself. We show
    that knowledge of the current state of the learner's
    representation, which is not available to an external agent, is
    necessary for selection of informative experiences. Hence it is
    advantageous if a learning system can select its own experiences.
    We show that the uncertainty of the current representation can be
    used as a heuristic to guide selection of experiences, and
    describe results obtained with DIDO, an inductive learning system
    we have developed using an uncertainty based selection heuristic.
  }

  }