Learning legal moves in planning problems: A connectionist approach to examining legal moves in the tower-of-hanoi

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.