Learning Hierarchical Task Networks from Plan Traces
نویسندگان
چکیده
We present HTN-MAKER, an offline and incremental algorithm for learning the structural relations between tasks in a Hierarchical Task Network (HTN). HTN-MAKER receives as input a STRIPS domain model, a collection of STRIPS plans, and a collection of task definitions, and produces an HTN domain model. HTN-MAKER is capable of learning an HTN domain model that reflects the provided task definitions. In particular, if the tasks have different levels of abstraction, these will be reflected in the HTN. We have conducted an empirical evaluation of HTN-MAKER on the logisticstransportation domain. These experiments demonstrate that HTN-MAKER quickly learns an HTN domain model that may be used to solve nearly all problems in the domain. Challenges and future work are discussed.
منابع مشابه
Learning task hierarchies using statistical semantics and goal reasoning
This paper describes WORD2HTN, an algorithm for learning hierarchical tasks and goals from plan traces in planning domains. WORD2HTN combines semantic text analysis techniques and subgoal learning in order to generate Hierarchical Task Networks (HTNs). Unlike existing HTN learning algorithms, WORD2HTN learns distributed vector representations that represent the similarities and semantics of the...
متن کاملLearning hierarchical task network domains from partially observed plan traces
Hierarchical Task Network (HTN) planning is an effective yet knowledge intensive problem-solving technique. It requires humans to encode knowledge in the form of methods and action models. Methods describe how to decompose tasks into subtasks and the preconditions under which those methods are applicable whereas action models describe how actions change the world. Encoding such knowledge is a d...
متن کاملLearning Probabilistic Hierarchical Task Networks from Plan Examples to Capture User Preference
Hierarchical task networks provide an efficient way to encode user prescriptions about what constitute good plans using component methods. However, manual construction of these methods is complex and time consuming. In this paper, we propose a novel approach to learning probabilistic hierarchical task networks that capture the user preference by examining user-produced plans given no prior info...
متن کاملLearning Plan Knowledge in Tasks with Information Gathering
In this paper we describe a framework for learning plan knowledge using expert solution traces in domains that include information-gathering tasks. We describe an extension to a special class of hierarchical task networks (HTNs) that can naturally represent information-gathering tasks and partial plans. We show how an existing analytical learning algorithm designed to learn a special form of HT...
متن کاملLearning Hierarchical Task Models from Input Traces
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 inf...
متن کامل