Inductive Generalization of Analytically Learned Goal Hierarchies

Könik, Tolga; Nejati, Negin; Kuter, Ugur

doi:10.1007/978-3-642-13840-9_7

Cited by 2 publications

(2 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Another valuable extension is improving the preconditions of the learned skills. While the main focus of this paper was learning the structure of the hierarchy, we are pursuing inductive logic programming techniques for learning better preconditions for the skills [7].…”

Section: Discussionmentioning

confidence: 99%

A goal- and dependency-directed algorithm for learning hierarchical task networks

Nejati

Könik

Kuter

2009

Proceedings of the Fifth International Conference on Knowledge Capture

Self Cite

View full text Add to dashboard Cite

This paper describes a system for learning domaindependent knowledge in the form of goal-indexed Hierarchical Task Networks (HTNs). DLIGHT is a goaldirected 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.

show abstract

Section: Discussionmentioning

confidence: 99%

A goal- and dependency-directed algorithm for learning hierarchical task networks

Nejati

Könik

Kuter

2009

Proceedings of the Fifth International Conference on Knowledge Capture

Self Cite

View full text Add to dashboard Cite

show abstract

“…Despite the great success of HTNs as a knowledge-modeling formalism, typically, a significant knowledge engineering burden is required to write HTN domain descriptions of planning domains. To alleviate this burden, there have been several advances in automated learning of hierarchical knowledge for planning (Reddy and Tadepalli 1997;Khardon 1999;Choi and Langley 2005;Ilghami et al 2005;Xu and Muñoz-Avila 2005;Könik and Laird 2006;Nejati et al 2006;Nejati, Könik, and Kuter 2009;Könik, Nejati, and Kuter 2009). Most of these works require as input some structural knowledge about the world and the relationships among the activities to be accomplished to achieve the objectives.…”

Section: Introductionmentioning

confidence: 99%

Learning Hierarchical Task Models from Input Traces

Hogg

Muñoz-Ávila

Kuter

2014

Computational Intelligence

Self Cite

View full text Add to dashboard Cite

We describe HTN-Maker, an algorithm for learning hierarchical planning knowledge in the form of task-reduction methods for Hierarchical Task Networks (HTNs). HTN-Maker takes as input a set of planning states from a classical planning domain and plans that are applicable to those states, as well as a set of semantically-annotated tasks to be accomplished. The algorithm analyzes this semantic information in order to determine which portion of the input plans accomplishes a particular task and constructs task-reduction methods based on those analyses.We present theoretical results showing that HTN-Maker is sound and complete. Our experiments in five well-known planning domains confirm the theoretical results and demonstrate convergence toward a set of HTN methods that can be used to solve any problem expressible as a classical planning problem in that domain, relative to a set of goal types for which tasks have been defined. In three of the five domains, HTN planning with the learned methods scales much better than a modern classical planner.

show abstract

Inductive Generalization of Analytically Learned Goal Hierarchies

Cited by 2 publications

References 9 publications

A goal- and dependency-directed algorithm for learning hierarchical task networks

A goal- and dependency-directed algorithm for learning hierarchical task networks

Learning Hierarchical Task Models from Input Traces

Contact Info

Product

Resources

About