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

Wenlong Huang, Pieter Abbeel, Deepak Pathak, Igor Mordatch

Keywords: GPT-3, Codex, LLMs, Language Models, Knowledge Extraction, Embodied Agents, Action Planning

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 (i.e. "make breakfast"), to a fixed set of actionable steps (i.e. "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 low-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. Videos at https://sites.google.com/view/language-model-as-planner

One-sentence Summary: We extract actionable knowledge from Codex to do action planning for embodied agents, without any additional training.

Community Implementations: [ 1 code implementation](https://www.catalyzex.com/paper/arxiv:2201.07207/code)