Preprint
Zero-Shot Iterative Formalization and Planning in Partially Observable Environments
ArXiv.org
19 May 2025
Abstract
Using LLMs not to predict plans but to formalize an environment into the
Planning Domain Definition Language (PDDL) has been shown to improve
performance and control. Existing work focuses on fully observable
environments; we tackle the more realistic and challenging partially observable
environments that lack of complete, reliable information. We propose PDDLego+,
a framework to iteratively formalize, plan, grow, and refine PDDL
representations in a zero-shot manner, without needing access to any existing
trajectories. On two textual simulated environments, we show that PDDLego+
improves goal reaching success and exhibits robustness against problem
complexity. We also show that the domain knowledge captured after a successful
trial can benefit future tasks.
Metrics
10 Record Views
Details
- Title
- Zero-Shot Iterative Formalization and Planning in Partially Observable Environments
- Creators
- Liancheng Gong - Drexel UniversityWang Zhu - University of Southern CaliforniaJesse Thomason - University of Southern CaliforniaLi Zhang - Drexel University, Computer Science
- Publication Details
- ArXiv.org
- Resource Type
- Preprint
- Language
- English
- Academic Unit
- Computer Science
- Other Identifier
- 991022122861404721