Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agents

Abstract

Can world knowledge learned by large language models (LLMs) be used to act in interactive environments? In this paper, we investigate the possibility of grounding high-level tasks, expressed in natural language (e.g. "make breakfast"), to a chosen set of actionable steps (e.g. "open fridge"). While prior work focused on learning from explicit step-by-step examples of how to act, we surprisingly find that if pre-trained LMs are large enough and prompted appropriately, they can effectively decompose high-level tasks into mid-level plans without any further training. However, the plans produced naively by LLMs often cannot map precisely to admissible actions. We propose a procedure that conditions on existing demonstrations and semantically translates the plans to admissible actions. Our evaluation in the recent VirtualHome environment shows that the resulting method substantially improves executability over the LLM baseline. The conducted human evaluation reveals a trade-off between executability and correctness but shows a promising sign towards extracting actionable knowledge from language models. Website at https://huangwl18.github.io/language-planner

arXiv commentProject website at https://huangwl18.github.io/language-planner

Cited by in corpus (14)

• Graph of Thoughts: Solving Elaborate Problems with Large Language Models
• ChatGPT Empowered Long-Step Robot Control in Various Environments: A Case Application
• Theory of Mind for Multi-Agent Collaboration via Large Language Models
• On the Prospects of Incorporating Large Language Models (LLMs) in Automated Planning and Scheduling (APS)
• Incremental Learning of Humanoid Robot Behavior from Natural Interaction and Large Language Models
• TR2MTL: LLM based framework for Metric Temporal Logic Formalization of Traffic Rules
• Ghost in the Minecraft: Generally Capable Agents for Open-World Environments via Large Language Models with Text-based Knowledge and Memory
• On Grounded Planning for Embodied Tasks with Language Models
• The Last JITAI? Exploring Large Language Models for Issuing Just-in-Time Adaptive Interventions: Fostering Physical Activity in a Conceptual Cardiac Rehabilitation Setting
• Do PLMs Know and Understand Ontological Knowledge?
• Multimedia Generative Script Learning for Task Planning
• Bootstrapping Cognitive Agents with a Large Language Model
• Remember what you did so you know what to do next
• Autonomous Task Completion Based on Goal-directed Answer Set Programming