Learning general search control from outside guidance

Authors:
Andrew Golding;Paul S. Rosenbloom;John E. Laird
Affiliations:
Computer Science Department, Stanford University, Stanford, CA;Computer Science Department, Stanford University, Stanford, CA;EECS Department, University of Michigan, Ann Arbor, MI
Venue:
IJCAI'87 Proceedings of the 10th international joint conference on Artificial intelligence - Volume 1
Year:
1987

Citing 2
Cited 2

SOAR: an architecture for general intelligence

Artificial Intelligence
Chunking in Soar: The Anatomy of a General Learning Mechanism

Machine Learning

Knowledge level learning in soar

AAAI'87 Proceedings of the sixth National conference on Artificial intelligence - Volume 2
Knowledge level learning in soar

AAAI'87 Proceedings of the sixth National conference on Artificial intelligence - Volume 2

Quantified Score

Hi-index	0.00

Visualization

Abstract

The system presented here shows how Soar, an architecture for general problem solving and learning, can acquire general search-control knowledge from outside guidance. The guidance can be either direct advice about what the system should do, or a problem that illustrates a relevant idea. The system makes use of the guidance by first formulating an appropriate goal for itself. In the process of achieving this goal, it learns general search-control chunks. In the case of learning from direct advice, the goal is to verify that the advice is correct. The verification allows the system to obtain general conditions of applicability of the advice, and to protect itself from erroneous advice. The system learns from illustrative problems by setting the goal of solving the problem provided. It can then transfer the lessons it learns along the way to its original problem. This transfer constitutes a rudimentary form of analogy.