ChatHTN: Interleaving Approximate (LLM) and Symbolic HTN Planning
Hector Munoz-Avila, David W. Aha, Paola Rizzo
TL;DR
ChatHTN is a hybrid planning system that combines symbolic HTN planning with ChatGPT queries to generate task hierarchies, ensuring soundness despite the approximate nature of ChatGPT's outputs.
Contribution
It introduces a novel interleaving approach that integrates symbolic HTN planning with ChatGPT, maintaining soundness in the generated plans.
Findings
ChatHTN produces sound task hierarchies.
The system effectively combines symbolic and neural planning methods.
Open-source implementation demonstrates practical viability.
Abstract
We introduce ChatHTN, a Hierarchical Task Network (HTN) planner that combines symbolic HTN planning techniques with queries to ChatGPT to approximate solutions in the form of task decompositions. The resulting hierarchies interleave task decompositions generated by symbolic HTN planning with those generated by ChatGPT. Despite the approximate nature of the results generates by ChatGPT, ChatHTN is provably sound; any plan it generates correctly achieves the input tasks. We demonstrate this property with an open-source implementation of our system.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsAI-based Problem Solving and Planning · Constraint Satisfaction and Optimization · Reinforcement Learning in Robotics