Learning legal moves in planning problems: A connectionist approach to examining legal moves in the tower-of-hanoi
Document Type
Article
Publication Date
1-1-1992
Abstract
While optimizing scheduling problems such as the Traveling Salesman Problem is relatively easy for neural networks, solving planning problems such as the Tower-of-Hanoi (ToH) of artificial intelligence has been known to be much more difficult. In this paper, the differences between the scheduling and planning problems have been identified from the neural network perspectives. This analysis is based on an approach used to solve planning problems with learning capabilities. In particular, the ToH is chosen as the target problem, and a set of constraints derived from the ToH has been formulated, based on the representation outlined in this paper. The system is designed to learn to generate legal moves by generating random illegal states and by measuring their legality. The approach described in this paper would establish a homogeneous structure which could be applied to planning problems which involve legality learning. © 1992.
Identifier
44049115348 (Scopus)
Publication Title
Engineering Applications of Artificial Intelligence
External Full Text Location
https://doi.org/10.1016/0952-1976(92)90007-7
ISSN
09521976
First Page
239
Last Page
245
Issue
3
Volume
5
Recommended Citation
Sohn, Andrew and Gaudiot, Jean Luc, "Learning legal moves in planning problems: A connectionist approach to examining legal moves in the tower-of-hanoi" (1992). Faculty Publications. 17336.
https://digitalcommons.njit.edu/fac_pubs/17336
