Few-shot Subgoal Planning with Language Models release_dn46md4hg5hqnogal5cmsrahru

by Lajanugen Logeswaran, Yao Fu, Moontae Lee, Honglak Lee

Released as a article .

2022  

Abstract

Pre-trained large language models have shown successful progress in many language understanding benchmarks. This work explores the capability of these models to predict actionable plans in real-world environments. Given a text instruction, we show that language priors encoded in pre-trained language models allow us to infer fine-grained subgoal sequences. In contrast to recent methods which make strong assumptions about subgoal supervision, our experiments show that language models can infer detailed subgoal sequences from few training sequences without any fine-tuning. We further propose a simple strategy to re-rank language model predictions based on interaction and feedback from the environment. Combined with pre-trained navigation and visual reasoning components, our approach demonstrates competitive performance on subgoal prediction and task completion in the ALFRED benchmark compared to prior methods that assume more subgoal supervision.
In text/plain format

Archived Files and Locations

application/pdf  1.2 MB
file_lfmo4bsu4zambdh26fns2733uy
arxiv.org (repository)
web.archive.org (webarchive)
Read Archived PDF
Preserved and Accessible
Type  article
Stage   submitted
Date   2022-05-28
Version   v1
Language   en ?
arXiv  2205.14288v1
Work Entity
access all versions, variants, and formats of this works (eg, pre-prints)
Catalog Record
Revision: 56de6094-948f-49a7-b6c1-a539fadd890d
API URL: JSON