Failsafe: a floor planner that uses EBG to learn from its failures

Authors:
Jack Mostow;Neeraj Bhatnagar
Affiliations:
Rutgers University, Computer Science Department, New Brunswick, New Jersey;Rutgers University, Computer Science Department, New Brunswick, New Jersey
Venue:
IJCAI'87 Proceedings of the 10th international joint conference on Artificial intelligence - Volume 1
Year:
1987

Citing 3
Cited 5

Chunking in Soar: The Anatomy of a General Learning Mechanism

Machine Learning
Explanation-Based Generalization: A Unifying View

Machine Learning
Mechanical transformation of task heuristics into operational procedures

Mechanical transformation of task heuristics into operational procedures

Adaptive search by explanation-based learning of heuristic censors

AAAI'90 Proceedings of the eighth National conference on Artificial intelligence - Volume 2
Extending EBG to term-rewriting systems

AAAI'90 Proceedings of the eighth National conference on Artificial intelligence - Volume 2
Regularity and structure

AAAI'91 Proceedings of the ninth National conference on Artificial intelligence - Volume 2
Constructive induction on domain information

AAAI'91 Proceedings of the ninth National conference on Artificial intelligence - Volume 2
Design and implementation of a replay framework based on a partial order planner

AAAI'96 Proceedings of the thirteenth national conference on Artificial intelligence - Volume 1

Quantified Score

Hi-index	0.01

Visualization

Abstract

Analysis of failed problem solving efforts enables people to guide subsequent problem solving to avoid similar failures. This kind of learning while doing is essential in complex domains. We define Explanation-based Learning from Failure (ELF), a technique for achieving such a capability, and describe its prototype implementation in Failsafe, a Prolog program that learns from failure while solving floor planning problems.