Seminar on Computational Learning and Adaptation

Learning Hierarchical Task Networks by Observation

Negin Nejati
Computational Learning Laboratory
Center for the Study of Language and Information
Stanford University
 

Knowledge-based planning methods offer benefits over classical techniques, but they are time consuming and costly to construct. There has been research on learning plan knowledge from search, but this can take substantial computer time and may even fail to find solutions on complex tasks.

In this talk, I describe another approach that observes sequences of operators taken from expert solutions to problems and learns hierarchical task networks from them. The method has similarities to previous algorithms for explanation-based learning, but differs in its ability to acquire hierarchical structures and in the generality of learned conditions. These increase the method's capability to transfer learned knowledge to other problems and supports the acquisition of recursive procedures. After presenting the learning algorithm, I report experiments that compare its abilities to other techniques on two planning domains. Finally, I discuss related work and directions for future research.

This talk describes joint work with Pat Langley and Tolga Konik.
 

Return to the seminar schedule