Planning as search: a quantitative approach
Artificial Intelligence
Watch what I do: programming by demonstration
Watch what I do: programming by demonstration
Learning Goal-Decomposition Rules using Exercises
ICML '97 Proceedings of the Fourteenth International Conference on Machine Learning
Learning approximate preconditions for methods in hierarchical plans
ICML '05 Proceedings of the 22nd international conference on Machine learning
Learning hierarchical task networks by observation
ICML '06 Proceedings of the 23rd international conference on Machine learning
A domain-independent system for case-based task decomposition without domain theories
AAAI'05 Proceedings of the 20th national conference on Artificial intelligence - Volume 1
HTN-MAKER: learning HTNs with minimal additional knowledge engineering required
AAAI'08 Proceedings of the 23rd national conference on Artificial intelligence - Volume 2
Journal of Artificial Intelligence Research
IJCAI'75 Proceedings of the 4th international joint conference on Artificial intelligence - Volume 1
LEAP: a learning apprentice for VLSI design
IJCAI'85 Proceedings of the 9th international joint conference on Artificial intelligence - Volume 1
Inductive generalization of analytically learned goal hierarchies
ILP'09 Proceedings of the 19th international conference on Inductive logic programming
Inductive generalization of analytically learned goal hierarchies
ILP'09 Proceedings of the 19th international conference on Inductive logic programming
Hi-index | 0.00 |
This paper describes a system for learning domain-dependent knowledge in the form of goal-indexed Hierarchical Task Networks (HTNs). DLIGHT is a goal-directed incremental learning algorithm which observes solution traces and generates rules for solving problems. One of the main challenges in learning this kind of knowledge is determining a good level of generality. Analytical methods, such as explanation-based macro-operator learning, construct very specific structures that guarantee a successful execution when applicable but generalize poorly to new problems. Previous goal-directed learning approaches produce hierarchical rules with more relaxed preconditions, but the learned knowledge suffers from over-generality. Our approach builds on one such approach but it strikes a better balance between generality and specificity. This is done by carrying out a goal-dependency analysis to determine the structure of the hierarchy and precondition of each rule to follow the successful solutions more closely while maintaining generality. We hypothesize that this algorithm produces HTNs that generalize well and can solve problems efficiently. We evaluate the system's behavior experimentally in several planning scenarios and conclude with related work and future research paths.