Online Learning of HTN Methods for integrated LLM HTN Planning

Yuesheng Xu, Hector Munoz-Avila

Keywords: Hierarchical Task Network (HTN), LLM, Planning, Online Learning

Abstract:

We present online learning of Hierarchical Task Network (HTN) methods in the context of inte-
grated HTN planning and LLM-based chatbots. Methods indicate when and how to decompose
tasks into subtasks. Our method learner is built on top of the ChatHTN planner. ChatHTN queries
ChatGPT to generate a decomposition of a task into primitive tasks when no applicable method for
the task is available. In this work, we extend ChatHTN. Namely, when ChatGPT generates a task
decomposition, ChatHTN learns from it, akin to memoization. However, unlike memoization, it
learns a generalized method that applies not only to the specific instance encountered, but to many
others. We conduct experiments on two domains and demonstrate that our online learning proce-
dure reduces the number of calls to ChatGPT while solving at least as many problems, and in some
cases, even more.

Paper Track: Technical paper

Submission Number: 15