Introduction to Reinforcement Learning
Introduction to Reinforcement Learning
Learning Goal-Decomposition Rules using Exercises
ICML '97 Proceedings of the Fourteenth International Conference on Machine Learning
Weak, strong, and strong cyclic planning via symbolic model checking
Artificial Intelligence - special issue on planning with uncertainty and incomplete information
Automated Planning: Theory & Practice
Automated Planning: Theory & Practice
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
Learning Recursive Control Programs from Problem Solving
The Journal of Machine Learning Research
Task decomposition on abstract states, for planning under nondeterminism
Artificial Intelligence
Forward-chaining planning in nondeterministic domains
AAAI'04 Proceedings of the 19th national conference on Artifical intelligence
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
Conditional progressive planning under uncertainty
IJCAI'01 Proceedings of the 17th international joint conference on Artificial intelligence - Volume 1
CPN-TWS: a coloured petri-net approach for transactional-QoS driven Web Service composition
International Journal of Web and Grid Services
iFALCON: A neural architecture for hierarchical planning
Neurocomputing
| Hi-index | 0.00 |
This paper describes how to learn Hierarchical Task Networks (HTNs) in nondeterministic planning domains, where actions may have multiple possible outcomes. We discuss several desired properties that guarantee that the resulting HTNs will correctly handle the nondeterminism in the domain. We developed a new learning algorithm, called HTN-MAKERND, that exploits these properties. We implemented HTN-MAKERND in the recently-proposed HTN-MAKER system, a goal-regression based HTN learning approach. In our theoretical study, we show that HTN-MAKERND soundly produces HTN planning knowledge in low-order polynomial times, despite the nondeterminism. In our experiments with two nondeterministic planning domains, ND-SHOP2, a well-known HTN planning algorithm for nondeterministic domains, significantly outperformed (in some cases, by about 3 orders of magnitude) the well-known planner MBP using the learned HTNs.