Learning action strategies for planning domains
Artificial Intelligence
Learning hierarchical task models by defining and refining examples
Proceedings of the 1st international conference on Knowledge capture
Learning Goal-Decomposition Rules using Exercises
ICML '97 Proceedings of the Fourteenth International Conference on Machine Learning
Learning Hierarchical Performance Knowledge by Observation
ICML '99 Proceedings of the Sixteenth International Conference on Machine Learning
Learning Declarative Control Rules for Constraint-BAsed Planning
ICML '00 Proceedings of the Seventeenth International Conference on Machine Learning
SHOP: Simple Hierarchical Ordered Planner
IJCAI '99 Proceedings of the Sixteenth International Joint Conference on Artificial Intelligence
Version spaces and the consistency problem
Artificial Intelligence
Version spaces without boundary sets
AAAI'97/IAAI'97 Proceedings of the fourteenth national conference on artificial intelligence and ninth conference on Innovative applications of artificial intelligence
A goal- and dependency-directed algorithm for learning hierarchical task networks
Proceedings of the fifth international conference on Knowledge capture
HTN-MAKER: learning HTNs with minimal additional knowledge engineering required
AAAI'08 Proceedings of the 23rd national conference on Artificial intelligence - Volume 2
Learning hierarchical task networks for nondeterministic planning domains
IJCAI'09 Proceedings of the 21st international jont conference on Artifical intelligence
Learning HTN method preconditions and action models from partial observations
IJCAI'09 Proceedings of the 21st international jont conference on Artifical intelligence
Transfer Learning for Reinforcement Learning Domains: A Survey
The Journal of Machine Learning Research
Inductive generalization of analytically learned goal hierarchies
ILP'09 Proceedings of the 19th international conference on Inductive logic programming
Hi-index | 0.00 |
A significant challenge in developing planning systems for practical applications is the difficulty of acquiring the domain knowledge needed by such systems. One method for acquiring this knowledge is to learn it from plan traces, but this method typically requires a huge number of plan traces to converge. In this paper, we show that the problem with slow convergence can be circumvented by having the learner generate solution plans even before the planning domain is completely learned. Our empirical results show that these improvements reduce the size of the training set that is needed to find correct answers to a large percentage of planning problems in the test set.